← Back to search
Epovest/mcp-server

Epovest

Make AIs recommend your business. Measures how AI assistants answer the questions your market asks, which sources they cite, and gives the levers to shape those answers. 43 tools on a hosted Streamable HTTP endpoint at https://mcp.epovest.com/mcp

DECISION SUMMARY
Production trust decision

Allow With Approval

Production readiness
Safe for evaluation
Score
68.2
Top 7.0% of 287 scored public servers. Live-validated, non-Failing servers with at least one inspected tool, ranked on the same publicly displayed score shown on this page.
Confidence
High
Based on evidence completeness, recency, and validation density.
Evidence age
11.7h old
Freshness: fresh. Snapshot trustsnap_d98e22cf57788997.
Top risk drivers
  • Request Association
  • Dependency Supply Chain Signal
  • Utility Coverage
Recommended actions
  • Add an explicit confirm/dry-run parameter or two-step confirmation flow to write, delete, exec, and egress-capable tool…
  • Align MCP-Protocol-Version, MCP-Session-Id, DELETE teardown, and expired-session handling with the transport spec.
  • Avoid removing tools, adding new required arguments, or changing outputSchema for tools already published to connector…
Next action
export policy, require approval for writes, add authenticated validation
write/admin actions need confirmation safeguards + high-risk tools need review + unauthenticated behavior not proven
Compare alternatives Export policy Open report JSON Dispute this assessment
Observed Attention
Low observed attention
AI discovery detected. This MCP server has recently appeared in AI-assisted discovery or evaluation traffic on Verify.
  • AI-assisted user activity
  • Search crawler activity
  • profile inspection
Bucketed signal based on recent segmented Verify telemetry. Crawler and evaluator activity is not treated as confirmed human demand.
Claim this profile to control the metadata agents are reading and publish verified ownership, security contact, policy metadata, badge status, and Intelligence API fields.
Status
Healthy
Score
68.2
Transport
streamable-http
Tools
66
DISPUTE THIS ASSESSMENT

Dispute this assessment

If any published claim about this server -- its score, a risk flag, a capability classification, or its taxonomy -- is factually wrong, tell us what evidence shows and we will review it. This does not require claiming or verifying ownership of the server first.

Verify responds to disputes within 5 business days and resolves them within 15.

Dispute history

No disputes filed for this server.

Risks

Security posture
Tools analyzed
66
High-risk tools
1
Destructive tools
5
Exec tools
0
Egress tools
10
Secret tools
0
Bulk-access tools
0
Risk distribution
low:32, medium:33, high:1
Tool capability & risk inventory
ToolCapabilitiesRiskFindingsNotesEvidence
list_trackers read Low none No explicit safeguard hints detected.
Schema & evidence
{
  "annotations": {
    "openWorldHint": false,
    "readOnlyHint": true
  },
  "capabilities": [
    "read"
  ],
  "input_schema": {
    "properties": {
      "project_id": {
        "description": "Only the trackers of this project: the UUID of a project of the account (call list_projects), or \"default\" for the trackers without a project. Omitted, every tracker is listed.",
        "type": "string"
      }
    },
    "type": "object"
  },
  "risk_flags": []
}
Dispute this classification
create_tracker write Medium freeform input surface No explicit safeguard hints detected.
Schema & evidence
{
  "annotations": {
    "destructiveHint": false,
    "idempotentHint": false,
    "openWorldHint": false,
    "readOnlyHint": false
  },
  "capabilities": [
    "write"
  ],
  "input_schema": {
    "properties": {
      "analysts": {
        "description": "The lenses that score every survey. keyword_presence and share_of_voice are deterministic; sentiment and custom_prompt are AI analysts billed per analyzed response.",
        "items": {
          "enum": [
            "keyword_presence",
            "share_of_voice",
            "sentiment",
            "custom_prompt"
          ],
          "type": "string"
        },
        "type": "array"
      },
      "custom_prompt": {
        "description": "The instruction of the custom_prompt analyst. Required when that analyst is selected.",
        "type": "string"
      },
      "discovery": {
        "description": "Suggest new keywords spotted in the answers.",
        "type": "boolean"
      },
      "engines": {
        "description": "The AI engines surveyed.",
        "items": {
          "enum": [
            "chatgpt",
            "claude",
            "gemini",
            "perplexity",
            "mistral",
            "grok"
          ],
          "type": "string"
        },
        "type": "array"
      },
      "frequency": {
        "description": "How often a survey runs.",
        "enum": [
          "monthly",
          "weekly",
          "daily"
        ],
        "type": "string"
      },
      "keywords": {
        "description": "Names to detect in the answers: your brand and the names you compare against. Flag yours as favorite.",
        "items": {
          "anyOf": [
            {
              "type": "string"
            },
            {
              "properties": {
                "favorite": {
                  "type": "boolean"
                },
                "keyword": {
                  "type": "string"
                }
              },
              "required": [
                "keyword"
              ],
              "type": "object"
            }
          ]
        },
        "type": "array"
      },
      "next_survey_at": {
        "description": "When the next survey runs, ISO 8601, strictly in the future; read as UTC without an offset. Later surveys keep that day and time at the pace of the frequency.",
        "type": "string"
      },
      "notify_on_survey": {
        "description": "Email the account owner and managers each time a survey closes with fresh data, so the results reach them on their own. On by default; send false to keep this tracker silent.",
        "type": "boolean"
      },
      "project_id": {
        "description": "The project the tracker is filed under: the UUID of a project of the account (call list_projects), or \"default\" for none. Pure organization, editable at any time. Omitted on creation the tracker files under Default; omitted on update the project does not change.",
        "type": "string"
      },
      "prompts": {
        "description": "The questions asked to the AI engines at every survey, phrased exactly as a customer would ask them.",
        "items": {
          "type": "string"
        },
        "type": "array"
      },
      "resolution": {
        "description": "Repetitions of every question per engine and survey: hd=1, full_hd=3, 4k=6, 8k=9. Answers are stochastic; more repetitions sharpen the rates.",
        "enum": [
          "hd",
          "full_hd",
          "4k",
          "8k"
        ],
        "type": "string"
      },
      "title": {
        "description": "Display name of the tracker.",
        "type": "string"
      }
    },
    "required": [
      "title",
      "prompts",
      "engines",
      "frequency",
      "resolution"
    ],
    "type": "object"
  },
  "risk_flags": [
    "freeform_input_surface"
  ]
}
Dispute this classification
update_tracker write Medium freeform input surface No explicit safeguard hints detected.
Schema & evidence
{
  "annotations": {
    "destructiveHint": false,
    "idempotentHint": false,
    "openWorldHint": false,
    "readOnlyHint": false
  },
  "capabilities": [
    "write"
  ],
  "input_schema": {
    "properties": {
      "analysts": {
        "description": "The lenses that score every survey. keyword_presence and share_of_voice are deterministic; sentiment and custom_prompt are AI analysts billed per analyzed response.",
        "items": {
          "enum": [
            "keyword_presence",
            "share_of_voice",
            "sentiment",
            "custom_prompt"
          ],
          "type": "string"
        },
        "type": "array"
      },
      "custom_prompt": {
        "description": "The instruction of the custom_prompt analyst. Required when that analyst is selected.",
        "type": "string"
      },
      "discovery": {
        "description": "Suggest new keywords spotted in the answers.",
        "type": "boolean"
      },
      "engines": {
        "description": "The AI engines surveyed.",
        "items": {
          "enum": [
            "chatgpt",
            "claude",
            "gemini",
            "perplexity",
            "mistral",
            "grok"
          ],
          "type": "string"
        },
        "type": "array"
      },
      "frequency": {
        "description": "How often a survey runs.",
        "enum": [
          "monthly",
          "weekly",
          "daily"
        ],
        "type": "string"
      },
      "keywords": {
        "description": "Names to detect in the answers: your brand and the names you compare against. Flag yours as favorite.",
        "items": {
          "anyOf": [
            {
              "type": "string"
            },
            {
              "properties": {
                "favorite": {
                  "type": "boolean"
                },
                "keyword": {
                  "type": "string"
                }
              },
              "required": [
                "keyword"
              ],
              "type": "object"
            }
          ]
        },
        "type": "array"
      },
      "next_survey_at": {
        "description": "When the next survey runs, ISO 8601, strictly in the future; read as UTC without an offset. Later surveys keep that day and time at the pace of the frequency.",
        "type": "string"
      },
      "notify_on_survey": {
        "description": "Email the account owner and managers each time a survey closes with fresh data, so the results reach them on their own. On by default; send false to keep this tracker silent.",
        "type": "boolean"
      },
      "project_id": {
        "description": "The project the tracker is filed under: the UUID of a project of the account (call list_projects), or \"default\" for none. Pure organization, editable at any time. Omitted on creation the tracker files under Default; omitted on update the project does not change.",
        "type": "string"
      },
      "prompts": {
        "description": "The questions asked to the AI engines at every survey, phrased exactly as a customer would ask them.",
        "items": {
          "type": "string"
        },
        "type": "array"
      },
      "resolution": {
        "description": "Repetitions of every question per engine and survey: hd=1, full_hd=3, 4k=6, 8k=9. Answers are stochastic; more repetitions sharpen the rates.",
        "enum": [
          "hd",
          "full_hd",
          "4k",
          "8k"
        ],
        "type": "string"
      },
      "title": {
        "description": "Display name of the tracker.",
        "type": "string"
      },
      "tracker_id": {
        "description": "The UUID of the tracker: call list_trackers to find it.",
        "format": "uuid",
        "type": "string"
      }
    },
    "required": [
      "tracker_id"
    ],
    "type": "object"
  },
  "risk_flags": [
    "freeform_input_surface"
  ]
}
Dispute this classification
start_tracker undetermined Low none No explicit safeguard hints detected.
Schema & evidence
{
  "annotations": {
    "destructiveHint": false,
    "idempotentHint": true,
    "openWorldHint": false,
    "readOnlyHint": false
  },
  "capabilities": [
    "undetermined"
  ],
  "input_schema": {
    "properties": {
      "tracker_id": {
        "description": "The UUID of the tracker: call list_trackers to find it.",
        "format": "uuid",
        "type": "string"
      }
    },
    "required": [
      "tracker_id"
    ],
    "type": "object"
  },
  "risk_flags": []
}
Dispute this classification
survey_now undetermined Low none No explicit safeguard hints detected.
Schema & evidence
{
  "annotations": {
    "destructiveHint": false,
    "idempotentHint": false,
    "openWorldHint": false,
    "readOnlyHint": false
  },
  "capabilities": [
    "undetermined"
  ],
  "input_schema": {
    "properties": {
      "tracker_id": {
        "description": "The UUID of the tracker: call list_trackers to find it.",
        "format": "uuid",
        "type": "string"
      }
    },
    "required": [
      "tracker_id"
    ],
    "type": "object"
  },
  "risk_flags": []
}
Dispute this classification
pause_tracker undetermined Low none No explicit safeguard hints detected.
Schema & evidence
{
  "annotations": {
    "destructiveHint": false,
    "idempotentHint": true,
    "openWorldHint": false,
    "readOnlyHint": false
  },
  "capabilities": [
    "undetermined"
  ],
  "input_schema": {
    "properties": {
      "tracker_id": {
        "description": "The UUID of the tracker: call list_trackers to find it.",
        "format": "uuid",
        "type": "string"
      }
    },
    "required": [
      "tracker_id"
    ],
    "type": "object"
  },
  "risk_flags": []
}
Dispute this classification
archive_tracker write delete Medium destructive operation No explicit safeguard hints detected.
Schema & evidence
{
  "annotations": {
    "destructiveHint": true,
    "idempotentHint": true,
    "openWorldHint": false,
    "readOnlyHint": false
  },
  "capabilities": [
    "write",
    "delete"
  ],
  "input_schema": {
    "properties": {
      "archived": {
        "description": "true files the tracker away and pauses its measurement, false brings it back. Omitted, it files it away.",
        "type": "boolean"
      },
      "tracker_id": {
        "description": "The UUID of the tracker: call list_trackers to find it.",
        "format": "uuid",
        "type": "string"
      }
    },
    "required": [
      "tracker_id"
    ],
    "type": "object"
  },
  "risk_flags": [
    "destructive_operation"
  ]
}
Dispute this classification
list_projects read Low none No explicit safeguard hints detected.
Schema & evidence
{
  "annotations": {
    "openWorldHint": false,
    "readOnlyHint": true
  },
  "capabilities": [
    "read"
  ],
  "input_schema": {
    "properties": {},
    "type": "object"
  },
  "risk_flags": []
}
Dispute this classification
create_project write Medium none No explicit safeguard hints detected.
Schema & evidence
{
  "annotations": {
    "destructiveHint": false,
    "idempotentHint": false,
    "openWorldHint": false,
    "readOnlyHint": false
  },
  "capabilities": [
    "write"
  ],
  "input_schema": {
    "properties": {
      "canon_address": {
        "description": "Postal address, as written on a listing. Language-neutral: the same string everywhere, like the other facts.",
        "type": "string"
      },
      "canon_category": {
        "description": "Category label for listings and structured data.",
        "type": "string"
      },
      "canon_email": {
        "description": "Public email address of the brand.",
        "type": "string"
      },
      "canon_language": {
        "description": "Short code of the ONE language the canon is written in, like \"en\" or \"pt-br\". The canonical language settles every language call (the llms.txt of a multilingual site is written in it). It travels WITH a wording: the canon is the wording, so sending the language on its own does not open one.",
        "type": "string"
      },
      "canon_legal_name": {
        "description": "Registered name of the company that operates the brand, with its jurisdiction when the user states it (\"Acme Holdings, LLC, Delaware, United States\"). Language-neutral, like the other facts: the AIs cross-read it to anchor the entity, and it is what a directory listing and an Organization.legalName block copy.",
        "type": "string"
      },
      "canon_long": {
        "description": "The two-sentence version, when the surface allows it.",
        "type": "string"
      },
      "canon_one_liner": {
        "description": "One-sentence signature of the brand.",
        "type": "string"
      },
      "canon_perks": {
        "description": "The distinctive claims of the brand, in the order they should be hammered, written in the canonical language. Facts that hold and can be corroborated (\"works without a subscription\"), never superlatives (\"the best\"), which no page reuses. A sent list REPLACES the previous one.",
        "items": {
          "type": "string"
        },
        "type": "array"
      },
      "canon_phone": {
        "description": "Phone number, international prefix included.",
        "type": "string"
      },
      "canon_short": {
        "description": "THE one-sentence description third-party pages reuse as is.",
        "type": "string"
      },
      "canon_website": {
        "description": "The canonical address of the brand website, the one that identifies the entity. A bare domain is enough (\"example.com\" completes to \"https://example.com\"). ONE URL only: the other addresses of the brand (documentation, application, blog, social accounts) are SURFACES, never a second canonical site.",
        "type": "string"
      },
      "canon_whatsapp": {
        "description": "WhatsApp number, international prefix included.",
        "type": "string"
      },
      "name": {
        "description": "Name of the project, as the user calls it (a client, a brand, a website...).",
        "type": "string"
      }
    },
    "required": [
      "name"
    ],
    "type": "object"
  },
  "risk_flags": []
}
Dispute this classification
rename_project undetermined Low none No explicit safeguard hints detected.
Schema & evidence
{
  "annotations": {
    "destructiveHint": false,
    "idempotentHint": true,
    "openWorldHint": false,
    "readOnlyHint": false
  },
  "capabilities": [
    "undetermined"
  ],
  "input_schema": {
    "properties": {
      "name": {
        "description": "The name the project takes, as the user calls it (a client, a brand, a website...).",
        "type": "string"
      },
      "project_id": {
        "description": "UUID of the project: call list_projects to find it.",
        "format": "uuid",
        "type": "string"
      }
    },
    "required": [
      "project_id",
      "name"
    ],
    "type": "object"
  },
  "risk_flags": []
}
Dispute this classification
get_canon read Low none No explicit safeguard hints detected.
Schema & evidence
{
  "annotations": {
    "openWorldHint": false,
    "readOnlyHint": true
  },
  "capabilities": [
    "read"
  ],
  "input_schema": {
    "properties": {
      "project_id": {
        "description": "UUID of the project: call list_projects to find it.",
        "format": "uuid",
        "type": "string"
      }
    },
    "required": [
      "project_id"
    ],
    "type": "object"
  },
  "risk_flags": []
}
Dispute this classification
update_project_canon write Medium none Safeguards hinted in metadata.
Schema & evidence
{
  "annotations": {
    "destructiveHint": false,
    "idempotentHint": true,
    "openWorldHint": false,
    "readOnlyHint": false
  },
  "capabilities": [
    "write"
  ],
  "input_schema": {
    "properties": {
      "canon_address": {
        "description": "Postal address, as written on a listing. Language-neutral: the same string everywhere, like the other facts.",
        "type": "string"
      },
      "canon_category": {
        "description": "Category label for listings and structured data.",
        "type": "string"
      },
      "canon_email": {
        "description": "Public email address of the brand.",
        "type": "string"
      },
      "canon_language": {
        "description": "Short code of the ONE language the canon is written in, like \"en\" or \"pt-br\". On a project whose canon is not posted yet, send it with at least one wording: the canon is the wording, and the language on its own does not open one.",
        "type": "string"
      },
      "canon_legal_name": {
        "description": "Registered name of the company that operates the brand, with its jurisdiction when the user states it (\"Acme Holdings, LLC, Delaware, United States\"). Language-neutral, like the other facts: the AIs cross-read it to anchor the entity, and it is what a directory listing and an Organization.legalName block copy.",
        "type": "string"
      },
      "canon_long": {
        "description": "The two-sentence version, when the surface allows it.",
        "type": "string"
      },
      "canon_one_liner": {
        "description": "One-sentence signature of the brand.",
        "type": "string"
      },
      "canon_perks": {
        "description": "The distinctive claims of the brand, in the order they should be hammered, written in the canonical language. Facts that hold and can be corroborated (\"works without a subscription\"), never superlatives (\"the best\"), which no page reuses. A sent list REPLACES the previous one.",
        "items": {
          "type": "string"
        },
        "type": "array"
      },
      "canon_phone": {
        "description": "Phone number, international prefix included.",
        "type": "string"
      },
      "canon_short": {
        "description": "THE one-sentence description third-party pages reuse as is.",
        "type": "string"
      },
      "canon_website": {
        "description": "The canonical address of the brand website, the one that identifies the entity. A bare domain is enough (\"example.com\" completes to \"https://example.com\"). ONE URL only: the other addresses of the brand (documentation, application, blog, social accounts) are SURFACES, never a second canonical site.",
        "type": "string"
      },
      "canon_whatsapp": {
        "description": "WhatsApp number, international prefix included.",
        "type": "string"
      },
      "project_id": {
        "description": "UUID of the project: call list_projects to find it.",
        "type": "string"
      }
    },
    "required": [
      "project_id"
    ],
    "type": "object"
  },
  "risk_flags": []
}
Dispute this classification
archive_project write delete Medium destructive operation No explicit safeguard hints detected.
Schema & evidence
{
  "annotations": {
    "destructiveHint": true,
    "idempotentHint": true,
    "openWorldHint": false,
    "readOnlyHint": false
  },
  "capabilities": [
    "write",
    "delete"
  ],
  "input_schema": {
    "properties": {
      "archived": {
        "description": "true files the project away, false brings it back. Omitted, it files it away.",
        "type": "boolean"
      },
      "project_id": {
        "description": "UUID of the project: call list_projects to find it.",
        "format": "uuid",
        "type": "string"
      }
    },
    "required": [
      "project_id"
    ],
    "type": "object"
  },
  "risk_flags": [
    "destructive_operation"
  ]
}
Dispute this classification
list_surfaces read Low none No explicit safeguard hints detected.
Schema & evidence
{
  "annotations": {
    "openWorldHint": false,
    "readOnlyHint": true
  },
  "capabilities": [
    "read"
  ],
  "input_schema": {
    "properties": {
      "deleted": {
        "description": "Set to \"only\" for the surfaces taken out of the registry (delete_surface), most recently taken out first, each with its deleted_at. Omitted, the registry is listed.",
        "enum": [
          "only"
        ],
        "type": "string"
      },
      "project_id": {
        "description": "UUID of the project: call list_projects to find it.",
        "format": "uuid",
        "type": "string"
      },
      "sort": {
        "description": "Order of the registry. \"registry\", the default, is the order of the binder, by shown name, the one where a known line is found again. \"authority\" orders by the measured authority of the DOMAIN of each line, the most read first, so the work follows a measured fact rather than the tidiness of a checkbox. It orders and never filters: every surface stays listed, the domains off the map closing the list, and a page nobody cites yet is sometimes exactly the one to work on.",
        "enum": [
          "registry",
          "authority"
        ],
        "type": "string"
      }
    },
    "required": [
      "project_id"
    ],
    "type": "object"
  },
  "risk_flags": []
}
Dispute this classification
create_surface write network Medium arbitrary network egress freeform input surface No explicit safeguard hints detected.
Schema & evidence
{
  "annotations": {
    "destructiveHint": false,
    "idempotentHint": false,
    "openWorldHint": false,
    "readOnlyHint": false
  },
  "capabilities": [
    "write",
    "network"
  ],
  "input_schema": {
    "properties": {
      "label": {
        "description": "Display name of the surface. OMIT IT on creation: it is derived from the url (the handle on a known place, the host and path on a website).",
        "type": "string"
      },
      "languages": {
        "description": "Languages of the surface, as short codes like \"en\" or \"pt-br\". A sent list replaces the previous one.",
        "items": {
          "type": "string"
        },
        "type": "array"
      },
      "notes": {
        "description": "Free registry notes: who owns the account, access, context.",
        "type": "string"
      },
      "project_id": {
        "description": "UUID of the project: call list_projects to find it.",
        "format": "uuid",
        "type": "string"
      },
      "type": {
        "description": "What kind of surface this is; it picks the checklist to come. OMIT IT on creation: the type is derived from the url by the catalogue of places (github.com is GitHub, an unknown host is the brand website). Send it only to correct a derivation. \"other\" covers anything else and carries the generic checklist.",
        "enum": [
          "website",
          "github",
          "linkedin",
          "x",
          "youtube",
          "wikidata",
          "directory",
          "app_store",
          "other"
        ],
        "type": "string"
      },
      "url": {
        "description": "Absolute http(s) address of the surface.",
        "type": "string"
      }
    },
    "required": [
      "project_id",
      "url"
    ],
    "type": "object"
  },
  "risk_flags": [
    "arbitrary_network_egress",
    "freeform_input_surface"
  ]
}
Dispute this classification
update_surface write network Medium arbitrary network egress freeform input surface No explicit safeguard hints detected.
Schema & evidence
{
  "annotations": {
    "destructiveHint": false,
    "idempotentHint": true,
    "openWorldHint": false,
    "readOnlyHint": false
  },
  "capabilities": [
    "write",
    "network"
  ],
  "input_schema": {
    "properties": {
      "label": {
        "description": "Display name of the surface. OMIT IT on creation: it is derived from the url (the handle on a known place, the host and path on a website).",
        "type": "string"
      },
      "languages": {
        "description": "Languages of the surface, as short codes like \"en\" or \"pt-br\". A sent list replaces the previous one.",
        "items": {
          "type": "string"
        },
        "type": "array"
      },
      "notes": {
        "description": "Free registry notes: who owns the account, access, context.",
        "type": "string"
      },
      "surface_id": {
        "description": "The UUID of the surface: call list_surfaces to find it.",
        "format": "uuid",
        "type": "string"
      },
      "type": {
        "description": "What kind of surface this is; it picks the checklist to come. OMIT IT on creation: the type is derived from the url by the catalogue of places (github.com is GitHub, an unknown host is the brand website). Send it only to correct a derivation. \"other\" covers anything else and carries the generic checklist.",
        "enum": [
          "website",
          "github",
          "linkedin",
          "x",
          "youtube",
          "wikidata",
          "directory",
          "app_store",
          "other"
        ],
        "type": "string"
      },
      "url": {
        "description": "Absolute http(s) address of the surface.",
        "type": "string"
      }
    },
    "required": [
      "surface_id"
    ],
    "type": "object"
  },
  "risk_flags": [
    "arbitrary_network_egress",
    "freeform_input_surface"
  ]
}
Dispute this classification
tick_surface_checklist write Medium none Safeguards hinted in metadata.
Schema & evidence
{
  "annotations": {
    "destructiveHint": false,
    "idempotentHint": true,
    "openWorldHint": false,
    "readOnlyHint": false
  },
  "capabilities": [
    "write"
  ],
  "input_schema": {
    "properties": {
      "surface_id": {
        "description": "The UUID of the surface: call list_surfaces to find it.",
        "format": "uuid",
        "type": "string"
      },
      "ticks": {
        "description": "The cell moves. Nothing else on the checklist changes.",
        "items": {
          "properties": {
            "dismissed": {
              "description": "true sets the cell aside (a \"reason\" is due), false brings it back to blank. Never combined with done.",
              "type": "boolean"
            },
            "done": {
              "description": "true verifies the cell, false clears it. Omitted (and no dismissed), it verifies.",
              "type": "boolean"
            },
            "item": {
              "description": "The item, exactly as listed by list_surfaces in checklist.items for the type of this surface.",
              "type": "string"
            },
            "language": {
              "description": "The language the cell belongs to, among the columns listed in checklist.state (\"default\" when the surface lists no language). Omitted, the single column of the surface is used; a multilingual surface needs it on every per-language item. A site-wide item (checklist.site_items) is one cell for the whole site: leave the language out.",
              "type": "string"
            },
            "reason": {
              "description": "Why the item does not apply on this surface, short: the exception must be readable without its author. Due when dismissed is true.",
              "type": "string"
            }
          },
          "required": [
            "item"
          ],
          "type": "object"
        },
        "type": "array"
      }
    },
    "required": [
      "surface_id",
      "ticks"
    ],
    "type": "object"
  },
  "risk_flags": []
}
Dispute this classification
add_surface_check write Medium none No explicit safeguard hints detected.
Schema & evidence
{
  "annotations": {
    "destructiveHint": false,
    "idempotentHint": true,
    "openWorldHint": false,
    "readOnlyHint": false
  },
  "capabilities": [
    "write"
  ],
  "input_schema": {
    "properties": {
      "label": {
        "description": "What the check says, as the person would read it on their checklist: one line, up to 120 characters (\"The FAQ block quotes the canon boilerplate\").",
        "type": "string"
      },
      "restates_canon": {
        "description": "true when the check restates the WORDING of the canon, so its verification perishes when the wording moves. false by default, for a check that constates something else.",
        "type": "boolean"
      },
      "scope": {
        "description": "How many cells the check gets: \"language\" by default, one per language of the surface; \"site\" for what exists once for the whole site whatever the number of languages.",
        "enum": [
          "site",
          "language"
        ],
        "type": "string"
      },
      "surface_id": {
        "description": "The UUID of the surface: call list_surfaces to find it.",
        "format": "uuid",
        "type": "string"
      }
    },
    "required": [
      "surface_id",
      "label"
    ],
    "type": "object"
  },
  "risk_flags": []
}
Dispute this classification
update_surface_check write Medium none No explicit safeguard hints detected.
Schema & evidence
{
  "annotations": {
    "destructiveHint": false,
    "idempotentHint": true,
    "openWorldHint": false,
    "readOnlyHint": false
  },
  "capabilities": [
    "write"
  ],
  "input_schema": {
    "properties": {
      "check": {
        "description": "The key of the check of your own, exactly as listed by list_surfaces in checklist.custom (add_surface_check returns it too).",
        "type": "string"
      },
      "label": {
        "description": "The new wording of the check, up to 120 characters.",
        "type": "string"
      },
      "restates_canon": {
        "description": "true when the check restates the WORDING of the canon, false when it constates something else.",
        "type": "boolean"
      },
      "surface_id": {
        "description": "The UUID of the surface: call list_surfaces to find it.",
        "format": "uuid",
        "type": "string"
      }
    },
    "required": [
      "surface_id",
      "check"
    ],
    "type": "object"
  },
  "risk_flags": []
}
Dispute this classification
delete_surface_check write delete Medium destructive operation No explicit safeguard hints detected.
Schema & evidence
{
  "annotations": {
    "destructiveHint": true,
    "idempotentHint": true,
    "openWorldHint": false,
    "readOnlyHint": false
  },
  "capabilities": [
    "write",
    "delete"
  ],
  "input_schema": {
    "properties": {
      "check": {
        "description": "The key of the check of your own, exactly as listed by list_surfaces in checklist.custom (add_surface_check returns it too).",
        "type": "string"
      },
      "surface_id": {
        "description": "The UUID of the surface: call list_surfaces to find it.",
        "format": "uuid",
        "type": "string"
      }
    },
    "required": [
      "surface_id",
      "check"
    ],
    "type": "object"
  },
  "risk_flags": [
    "destructive_operation"
  ]
}
Dispute this classification
restore_surface_check undetermined Low none No explicit safeguard hints detected.
Schema & evidence
{
  "annotations": {
    "destructiveHint": false,
    "idempotentHint": true,
    "openWorldHint": false,
    "readOnlyHint": false
  },
  "capabilities": [
    "undetermined"
  ],
  "input_schema": {
    "properties": {
      "check": {
        "description": "The key of the check of your own, exactly as listed by list_surfaces in checklist.custom (add_surface_check returns it too).",
        "type": "string"
      },
      "surface_id": {
        "description": "The UUID of the surface: call list_surfaces to find it.",
        "format": "uuid",
        "type": "string"
      }
    },
    "required": [
      "surface_id",
      "check"
    ],
    "type": "object"
  },
  "risk_flags": []
}
Dispute this classification
delete_surface write delete Medium destructive operation No explicit safeguard hints detected.
Schema & evidence
{
  "annotations": {
    "destructiveHint": true,
    "idempotentHint": true,
    "openWorldHint": false,
    "readOnlyHint": false
  },
  "capabilities": [
    "write",
    "delete"
  ],
  "input_schema": {
    "properties": {
      "surface_id": {
        "description": "The UUID of the surface: call list_surfaces to find it.",
        "format": "uuid",
        "type": "string"
      }
    },
    "required": [
      "surface_id"
    ],
    "type": "object"
  },
  "risk_flags": [
    "destructive_operation"
  ]
}
Dispute this classification
restore_surface undetermined Low none No explicit safeguard hints detected.
Schema & evidence
{
  "annotations": {
    "destructiveHint": false,
    "idempotentHint": true,
    "openWorldHint": false,
    "readOnlyHint": false
  },
  "capabilities": [
    "undetermined"
  ],
  "input_schema": {
    "properties": {
      "surface_id": {
        "description": "The UUID of the surface: call list_surfaces to find it.",
        "format": "uuid",
        "type": "string"
      }
    },
    "required": [
      "surface_id"
    ],
    "type": "object"
  },
  "risk_flags": []
}
Dispute this classification
convert_surface_to_corroboration undetermined Low none Safeguards hinted in metadata.
Schema & evidence
{
  "annotations": {
    "destructiveHint": false,
    "idempotentHint": true,
    "openWorldHint": false,
    "readOnlyHint": false
  },
  "capabilities": [
    "undetermined"
  ],
  "input_schema": {
    "properties": {
      "surface_id": {
        "description": "The UUID of the surface: call list_surfaces to find it.",
        "format": "uuid",
        "type": "string"
      }
    },
    "required": [
      "surface_id"
    ],
    "type": "object"
  },
  "risk_flags": []
}
Dispute this classification
list_corroborations read Low none No explicit safeguard hints detected.
Schema & evidence
{
  "annotations": {
    "openWorldHint": false,
    "readOnlyHint": true
  },
  "capabilities": [
    "read"
  ],
  "input_schema": {
    "properties": {
      "project_id": {
        "description": "UUID of the project: call list_projects to find it.",
        "format": "uuid",
        "type": "string"
      }
    },
    "required": [
      "project_id"
    ],
    "type": "object"
  },
  "risk_flags": []
}
Dispute this classification
create_corroboration write network Medium arbitrary network egress freeform input surface Safeguards hinted in metadata.
Schema & evidence
{
  "annotations": {
    "destructiveHint": false,
    "idempotentHint": false,
    "openWorldHint": false,
    "readOnlyHint": false
  },
  "capabilities": [
    "write",
    "network"
  ],
  "input_schema": {
    "properties": {
      "label": {
        "description": "Display name of the page. OMIT IT: it is derived from the address (domain and path). Send an empty string to go back to the derived one.",
        "type": "string"
      },
      "notes": {
        "description": "Free notes: the passage that mentions the brand, the contact, how the page came about.",
        "type": "string"
      },
      "project_id": {
        "description": "UUID of the project: call list_projects to find it.",
        "format": "uuid",
        "type": "string"
      },
      "published_on": {
        "description": "The day the page was PUBLISHED, as YYYY-MM-DD. Distinct from the recording day, and the one that means something against the citation curves. Omit it when unknown: it is never guessed.",
        "type": "string"
      },
      "request_channel": {
        "description": "Whether someone can be asked to change the page: \"available\" (a contact or a process exists), \"none\" (nobody to ask), \"unknown\" (not filled in, the default). It gates the refresh suggestions of the quest file; the contact itself belongs in the notes.",
        "enum": [
          "available",
          "none",
          "unknown"
        ],
        "type": "string"
      },
      "url": {
        "description": "Absolute http(s) address of the EXACT page where the third party talks about the brand, never the home page of the site.",
        "type": "string"
      }
    },
    "required": [
      "project_id",
      "url"
    ],
    "type": "object"
  },
  "risk_flags": [
    "arbitrary_network_egress",
    "freeform_input_surface"
  ]
}
Dispute this classification
update_corroboration write network Medium arbitrary network egress freeform input surface No explicit safeguard hints detected.
Schema & evidence
{
  "annotations": {
    "destructiveHint": false,
    "idempotentHint": true,
    "openWorldHint": false,
    "readOnlyHint": false
  },
  "capabilities": [
    "write",
    "network"
  ],
  "input_schema": {
    "properties": {
      "corroboration_id": {
        "description": "The UUID of the corroboration: call list_corroborations to find it.",
        "format": "uuid",
        "type": "string"
      },
      "label": {
        "description": "Display name of the page. OMIT IT: it is derived from the address (domain and path). Send an empty string to go back to the derived one.",
        "type": "string"
      },
      "monitoring": {
        "description": "How often the page is read again on its own: \"off\" (the default), \"daily\", \"weekly\" or \"monthly\". Each executed check costs 0.02 USD from the prepaid balance and returns the same two findings as verify_corroboration, on the mention and on the link, plus an email when the text of the passage changed or the link is gone. It states a STATE, so sending the same value again does nothing. It applies to a live line whose page reads (readability \"html\"): elsewhere the reply is 409 corroboration_archived or 409 page_not_readable, and \"off\" is always accepted.",
        "enum": [
          "off",
          "daily",
          "weekly",
          "monthly"
        ],
        "type": "string"
      },
      "notes": {
        "description": "Free notes: the passage that mentions the brand, the contact, how the page came about.",
        "type": "string"
      },
      "published_on": {
        "description": "The day the page was PUBLISHED, as YYYY-MM-DD. Distinct from the recording day, and the one that means something against the citation curves. Omit it when unknown: it is never guessed.",
        "type": "string"
      },
      "request_channel": {
        "description": "Whether someone can be asked to change the page: \"available\" (a contact or a process exists), \"none\" (nobody to ask), \"unknown\" (not filled in, the default). It gates the refresh suggestions of the quest file; the contact itself belongs in the notes.",
        "enum": [
          "available",
          "none",
          "unknown"
        ],
        "type": "string"
      },
      "url": {
        "description": "Absolute http(s) address of the EXACT page where the third party talks about the brand, never the home page of the site.",
        "type": "string"
      }
    },
    "required": [
      "corroboration_id"
    ],
    "type": "object"
  },
  "risk_flags": [
    "arbitrary_network_egress",
    "freeform_input_surface"
  ]
}
Dispute this classification
archive_corroboration write Medium none No explicit safeguard hints detected.
Schema & evidence
{
  "annotations": {
    "destructiveHint": false,
    "idempotentHint": true,
    "openWorldHint": false,
    "readOnlyHint": false
  },
  "capabilities": [
    "write"
  ],
  "input_schema": {
    "properties": {
      "archived": {
        "description": "true takes the page down, false puts it back live. Omitted, it takes it down.",
        "type": "boolean"
      },
      "corroboration_id": {
        "description": "The UUID of the corroboration: call list_corroborations to find it.",
        "format": "uuid",
        "type": "string"
      }
    },
    "required": [
      "corroboration_id"
    ],
    "type": "object"
  },
  "risk_flags": []
}
Dispute this classification
verify_corroboration network Medium arbitrary network egress No explicit safeguard hints detected.
Schema & evidence
{
  "annotations": {
    "destructiveHint": false,
    "idempotentHint": true,
    "openWorldHint": true,
    "readOnlyHint": false
  },
  "capabilities": [
    "network"
  ],
  "input_schema": {
    "properties": {
      "corroboration_id": {
        "description": "The UUID of the corroboration: call list_corroborations to find it.",
        "format": "uuid",
        "type": "string"
      }
    },
    "required": [
      "corroboration_id"
    ],
    "type": "object"
  },
  "risk_flags": [
    "arbitrary_network_egress"
  ]
}
Dispute this classification
convert_corroboration_to_surface undetermined Low none Safeguards hinted in metadata.
Schema & evidence
{
  "annotations": {
    "destructiveHint": false,
    "idempotentHint": true,
    "openWorldHint": false,
    "readOnlyHint": false
  },
  "capabilities": [
    "undetermined"
  ],
  "input_schema": {
    "properties": {
      "corroboration_id": {
        "description": "The UUID of the corroboration: call list_corroborations to find it.",
        "format": "uuid",
        "type": "string"
      }
    },
    "required": [
      "corroboration_id"
    ],
    "type": "object"
  },
  "risk_flags": []
}
Dispute this classification
list_corroboration_candidates read Low none No explicit safeguard hints detected.
Schema & evidence
{
  "annotations": {
    "openWorldHint": false,
    "readOnlyHint": true
  },
  "capabilities": [
    "read"
  ],
  "input_schema": {
    "properties": {
      "project_id": {
        "description": "UUID of the project: call list_projects to find it.",
        "format": "uuid",
        "type": "string"
      }
    },
    "required": [
      "project_id"
    ],
    "type": "object"
  },
  "risk_flags": []
}
Dispute this classification
dismiss_corroboration_candidate network Medium arbitrary network egress freeform input surface No explicit safeguard hints detected.
Schema & evidence
{
  "annotations": {
    "destructiveHint": false,
    "idempotentHint": true,
    "openWorldHint": false,
    "readOnlyHint": false
  },
  "capabilities": [
    "network"
  ],
  "input_schema": {
    "properties": {
      "project_id": {
        "description": "UUID of the project: call list_projects to find it.",
        "format": "uuid",
        "type": "string"
      },
      "url": {
        "description": "The address of the candidate, exactly as list_corroboration_candidates gives it.",
        "type": "string"
      }
    },
    "required": [
      "project_id",
      "url"
    ],
    "type": "object"
  },
  "risk_flags": [
    "arbitrary_network_egress",
    "freeform_input_surface"
  ]
}
Dispute this classification
get_logbook read Low none No explicit safeguard hints detected.
Schema & evidence
{
  "annotations": {
    "openWorldHint": false,
    "readOnlyHint": true
  },
  "capabilities": [
    "read"
  ],
  "input_schema": {
    "properties": {
      "category": {
        "description": "Only the manual entries of this category (tool events carry no category and never match).",
        "enum": [
          "content",
          "technical",
          "translation",
          "canon",
          "press",
          "other"
        ],
        "type": "string"
      },
      "deleted": {
        "description": "Set to \"only\" for the entries taken out of the logbook (delete_logbook_entry), most recently taken out first, each with its deleted_at. It carries recorded entries only, so it goes without source and category. Omitted, the logbook is read.",
        "enum": [
          "only"
        ],
        "type": "string"
      },
      "project_id": {
        "description": "UUID of the project: call list_projects to find it.",
        "format": "uuid",
        "type": "string"
      },
      "source": {
        "description": "Only the items of this source: \"tool\" for suite events, \"manual\" for recorded entries. Omitted, both.",
        "enum": [
          "tool",
          "manual"
        ],
        "type": "string"
      }
    },
    "required": [
      "project_id"
    ],
    "type": "object"
  },
  "risk_flags": []
}
Dispute this classification
create_logbook_entry write Medium none No explicit safeguard hints detected.
Schema & evidence
{
  "annotations": {
    "destructiveHint": false,
    "idempotentHint": false,
    "openWorldHint": false,
    "readOnlyHint": false
  },
  "capabilities": [
    "write"
  ],
  "input_schema": {
    "properties": {
      "category": {
        "description": "What kind of action this is; it files the entry for filtering. \"other\" covers anything else.",
        "enum": [
          "content",
          "technical",
          "translation",
          "canon",
          "press",
          "other"
        ],
        "type": "string"
      },
      "label": {
        "description": "Short wording of the action, e.g. \"Site translated into Spanish\": it is what the annotation shows next to the citation curves.",
        "type": "string"
      },
      "notes": {
        "description": "Free notes: context, links, details of the action.",
        "type": "string"
      },
      "occurred_at": {
        "description": "When the action HAPPENED, ISO 8601 date or datetime, read as UTC without an offset. Distinct from the recording time: when the user says \"yesterday\" or \"last week\", compute and pass that date. Omitted on creation, now is used.",
        "type": "string"
      },
      "project_id": {
        "description": "UUID of the project: call list_projects to find it.",
        "format": "uuid",
        "type": "string"
      }
    },
    "required": [
      "project_id",
      "category",
      "label"
    ],
    "type": "object"
  },
  "risk_flags": []
}
Dispute this classification
update_logbook_entry write Medium none No explicit safeguard hints detected.
Schema & evidence
{
  "annotations": {
    "destructiveHint": false,
    "idempotentHint": true,
    "openWorldHint": false,
    "readOnlyHint": false
  },
  "capabilities": [
    "write"
  ],
  "input_schema": {
    "properties": {
      "category": {
        "description": "What kind of action this is; it files the entry for filtering. \"other\" covers anything else.",
        "enum": [
          "content",
          "technical",
          "translation",
          "canon",
          "press",
          "other"
        ],
        "type": "string"
      },
      "entry_id": {
        "description": "The UUID of the logbook entry: call get_logbook to find it (only manual entries carry an id).",
        "format": "uuid",
        "type": "string"
      },
      "label": {
        "description": "Short wording of the action, e.g. \"Site translated into Spanish\": it is what the annotation shows next to the citation curves.",
        "type": "string"
      },
      "notes": {
        "description": "Free notes: context, links, details of the action.",
        "type": "string"
      },
      "occurred_at": {
        "description": "When the action HAPPENED, ISO 8601 date or datetime, read as UTC without an offset. Distinct from the recording time: when the user says \"yesterday\" or \"last week\", compute and pass that date. Omitted on creation, now is used.",
        "type": "string"
      }
    },
    "required": [
      "entry_id"
    ],
    "type": "object"
  },
  "risk_flags": []
}
Dispute this classification
delete_logbook_entry write delete Medium destructive operation No explicit safeguard hints detected.
Schema & evidence
{
  "annotations": {
    "destructiveHint": true,
    "idempotentHint": true,
    "openWorldHint": false,
    "readOnlyHint": false
  },
  "capabilities": [
    "write",
    "delete"
  ],
  "input_schema": {
    "properties": {
      "entry_id": {
        "description": "The UUID of the logbook entry: call get_logbook to find it (only manual entries carry an id).",
        "format": "uuid",
        "type": "string"
      }
    },
    "required": [
      "entry_id"
    ],
    "type": "object"
  },
  "risk_flags": [
    "destructive_operation"
  ]
}
Dispute this classification
restore_logbook_entry undetermined Low none No explicit safeguard hints detected.
Schema & evidence
{
  "annotations": {
    "destructiveHint": false,
    "idempotentHint": true,
    "openWorldHint": false,
    "readOnlyHint": false
  },
  "capabilities": [
    "undetermined"
  ],
  "input_schema": {
    "properties": {
      "entry_id": {
        "description": "The UUID of the logbook entry: call get_logbook to find it (only manual entries carry an id).",
        "format": "uuid",
        "type": "string"
      }
    },
    "required": [
      "entry_id"
    ],
    "type": "object"
  },
  "risk_flags": []
}
Dispute this classification
list_quests read Low none Safeguards hinted in metadata.
Schema & evidence
{
  "annotations": {
    "openWorldHint": false,
    "readOnlyHint": true
  },
  "capabilities": [
    "read"
  ],
  "input_schema": {
    "properties": {
      "project_id": {
        "description": "Only the file of this project: the UUID of a project of the account (call list_projects). Omitted, the file covers every active project.",
        "format": "uuid",
        "type": "string"
      },
      "status": {
        "description": "Which quests to list: \"open\" (the file, default), \"done\" or \"dismissed\" (the closed history).",
        "enum": [
          "open",
          "done",
          "dismissed"
        ],
        "type": "string"
      }
    },
    "type": "object"
  },
  "risk_flags": []
}
Dispute this classification
create_quest write Medium none No explicit safeguard hints detected.
Schema & evidence
{
  "annotations": {
    "destructiveHint": false,
    "idempotentHint": false,
    "openWorldHint": false,
    "readOnlyHint": false
  },
  "capabilities": [
    "write"
  ],
  "input_schema": {
    "properties": {
      "notes": {
        "description": "Free notes: context, links, what done looks like.",
        "type": "string"
      },
      "project_id": {
        "description": "UUID of the project whose file takes the quest: call list_projects to find it.",
        "format": "uuid",
        "type": "string"
      },
      "title": {
        "description": "Short wording of the move, e.g. \"Get our MCP server listed on the AI tool directories\": it is what the file shows.",
        "type": "string"
      }
    },
    "required": [
      "project_id",
      "title"
    ],
    "type": "object"
  },
  "risk_flags": []
}
Dispute this classification
update_quest write Medium none No explicit safeguard hints detected.
Schema & evidence
{
  "annotations": {
    "destructiveHint": false,
    "idempotentHint": true,
    "openWorldHint": false,
    "readOnlyHint": false
  },
  "capabilities": [
    "write"
  ],
  "input_schema": {
    "properties": {
      "notes": {
        "description": "Free notes: context, links, what done looks like.",
        "type": "string"
      },
      "quest_id": {
        "description": "The UUID of the quest: call list_quests to find it.",
        "format": "uuid",
        "type": "string"
      },
      "title": {
        "description": "Short wording of the move, e.g. \"Get our MCP server listed on the AI tool directories\": it is what the file shows.",
        "type": "string"
      }
    },
    "required": [
      "quest_id"
    ],
    "type": "object"
  },
  "risk_flags": []
}
Dispute this classification
complete_quest undetermined Low none No explicit safeguard hints detected.
Schema & evidence
{
  "annotations": {
    "destructiveHint": false,
    "idempotentHint": true,
    "openWorldHint": false,
    "readOnlyHint": false
  },
  "capabilities": [
    "undetermined"
  ],
  "input_schema": {
    "properties": {
      "quest_id": {
        "description": "The UUID of the quest: call list_quests to find it.",
        "format": "uuid",
        "type": "string"
      }
    },
    "required": [
      "quest_id"
    ],
    "type": "object"
  },
  "risk_flags": []
}
Dispute this classification
dismiss_quest undetermined Low none No explicit safeguard hints detected.
Schema & evidence
{
  "annotations": {
    "destructiveHint": false,
    "idempotentHint": true,
    "openWorldHint": false,
    "readOnlyHint": false
  },
  "capabilities": [
    "undetermined"
  ],
  "input_schema": {
    "properties": {
      "quest_id": {
        "description": "The UUID of the quest: call list_quests to find it.",
        "format": "uuid",
        "type": "string"
      }
    },
    "required": [
      "quest_id"
    ],
    "type": "object"
  },
  "risk_flags": []
}
Dispute this classification
reopen_quest write Medium none No explicit safeguard hints detected.
Schema & evidence
{
  "annotations": {
    "destructiveHint": false,
    "idempotentHint": true,
    "openWorldHint": false,
    "readOnlyHint": false
  },
  "capabilities": [
    "write"
  ],
  "input_schema": {
    "properties": {
      "quest_id": {
        "description": "The UUID of the quest: call list_quests to find it.",
        "format": "uuid",
        "type": "string"
      }
    },
    "required": [
      "quest_id"
    ],
    "type": "object"
  },
  "risk_flags": []
}
Dispute this classification
get_results read Low none No explicit safeguard hints detected.
Schema & evidence
{
  "annotations": {
    "openWorldHint": false,
    "readOnlyHint": true
  },
  "capabilities": [
    "read"
  ],
  "input_schema": {
    "properties": {
      "analyst": {
        "description": "Only the rows of this analyst. The custom_prompt analyst yields a text note per response, so the score series is built from the three scored lenses listed here.",
        "enum": [
          "keyword_presence",
          "share_of_voice",
          "sentiment"
        ],
        "type": "string"
      },
      "engine": {
        "description": "Only the rows of this engine.",
        "enum": [
          "chatgpt",
          "claude",
          "gemini",
          "perplexity",
          "mistral",
          "grok"
        ],
        "type": "string"
      },
      "tracker_id": {
        "description": "The UUID of the tracker: call list_trackers to find it.",
        "format": "uuid",
        "type": "string"
      }
    },
    "required": [
      "tracker_id"
    ],
    "type": "object"
  },
  "risk_flags": []
}
Dispute this classification
get_responses read Low none Safeguards hinted in metadata.
Schema & evidence
{
  "annotations": {
    "openWorldHint": false,
    "readOnlyHint": true
  },
  "capabilities": [
    "read"
  ],
  "input_schema": {
    "properties": {
      "engine": {
        "description": "The engine whose answers are read.",
        "enum": [
          "chatgpt",
          "claude",
          "gemini",
          "perplexity",
          "mistral",
          "grok"
        ],
        "type": "string"
      },
      "include_raw": {
        "description": "Add the full engine payload to every answer.",
        "type": "boolean"
      },
      "page": {
        "description": "Page number, 1 by default.",
        "minimum": 1,
        "type": "integer"
      },
      "per_page": {
        "description": "Answers per page, 25 by default, 100 at most.",
        "maximum": 100,
        "minimum": 1,
        "type": "integer"
      },
      "q": {
        "description": "Full-text filter on the answer text.",
        "type": "string"
      },
      "question": {
        "description": "Exact text of one tracked question.",
        "type": "string"
      },
      "survey": {
        "description": "Only the answers of this survey.",
        "format": "uuid",
        "type": "string"
      },
      "tone": {
        "description": "Only the answers where the sentiment analyst judged a keyword mention with this tone. Reads the negative answers of a week in one call, when the tracker carries the sentiment analyst that sets the tone.",
        "enum": [
          "positive",
          "neutral",
          "negative"
        ],
        "type": "string"
      },
      "tracker_id": {
        "description": "The UUID of the tracker: call list_trackers to find it.",
        "format": "uuid",
        "type": "string"
      }
    },
    "required": [
      "tracker_id",
      "engine"
    ],
    "type": "object"
  },
  "risk_flags": []
}
Dispute this classification
list_keyword_discoveries read Low none No explicit safeguard hints detected.
Schema & evidence
{
  "annotations": {
    "openWorldHint": false,
    "readOnlyHint": true
  },
  "capabilities": [
    "read"
  ],
  "input_schema": {
    "properties": {
      "tracker_id": {
        "description": "The UUID of the tracker: call list_trackers to find it.",
        "format": "uuid",
        "type": "string"
      }
    },
    "required": [
      "tracker_id"
    ],
    "type": "object"
  },
  "risk_flags": []
}
Dispute this classification
accept_keyword_discovery write network Medium arbitrary network egress freeform input surface No explicit safeguard hints detected.
Schema & evidence
{
  "annotations": {
    "destructiveHint": false,
    "idempotentHint": false,
    "openWorldHint": false,
    "readOnlyHint": false
  },
  "capabilities": [
    "write",
    "network"
  ],
  "input_schema": {
    "properties": {
      "domain": {
        "description": "One domain to act on, exactly as listed by list_keyword_discoveries. Send this OR domains, never both.",
        "type": "string"
      },
      "domains": {
        "description": "Several domains to act on in one call, each exactly as listed by list_keyword_discoveries. Send this OR domain, never both. ALL-OR-NOTHING: one invalid domain refuses the whole batch, so you never have to guess which half took.",
        "items": {
          "type": "string"
        },
        "type": "array"
      },
      "tracker_id": {
        "description": "The UUID of the tracker: call list_trackers to find it.",
        "format": "uuid",
        "type": "string"
      }
    },
    "required": [
      "tracker_id"
    ],
    "type": "object"
  },
  "risk_flags": [
    "arbitrary_network_egress",
    "freeform_input_surface"
  ]
}
Dispute this classification
dismiss_keyword_discovery write network Medium arbitrary network egress freeform input surface No explicit safeguard hints detected.
Schema & evidence
{
  "annotations": {
    "destructiveHint": false,
    "idempotentHint": true,
    "openWorldHint": false,
    "readOnlyHint": false
  },
  "capabilities": [
    "write",
    "network"
  ],
  "input_schema": {
    "properties": {
      "domain": {
        "description": "One domain to act on, exactly as listed by list_keyword_discoveries. Send this OR domains, never both.",
        "type": "string"
      },
      "domains": {
        "description": "Several domains to act on in one call, each exactly as listed by list_keyword_discoveries. Send this OR domain, never both. ALL-OR-NOTHING: one invalid domain refuses the whole batch, so you never have to guess which half took.",
        "items": {
          "type": "string"
        },
        "type": "array"
      },
      "tracker_id": {
        "description": "The UUID of the tracker: call list_trackers to find it.",
        "format": "uuid",
        "type": "string"
      }
    },
    "required": [
      "tracker_id"
    ],
    "type": "object"
  },
  "risk_flags": [
    "arbitrary_network_egress",
    "freeform_input_surface"
  ]
}
Dispute this classification
restore_keyword_discovery write network Medium arbitrary network egress freeform input surface No explicit safeguard hints detected.
Schema & evidence
{
  "annotations": {
    "destructiveHint": false,
    "idempotentHint": true,
    "openWorldHint": false,
    "readOnlyHint": false
  },
  "capabilities": [
    "write",
    "network"
  ],
  "input_schema": {
    "properties": {
      "domain": {
        "description": "One domain to act on, exactly as listed by list_keyword_discoveries. Send this OR domains, never both.",
        "type": "string"
      },
      "domains": {
        "description": "Several domains to act on in one call, each exactly as listed by list_keyword_discoveries. Send this OR domain, never both. ALL-OR-NOTHING: one invalid domain refuses the whole batch, so you never have to guess which half took.",
        "items": {
          "type": "string"
        },
        "type": "array"
      },
      "tracker_id": {
        "description": "The UUID of the tracker: call list_trackers to find it.",
        "format": "uuid",
        "type": "string"
      }
    },
    "required": [
      "tracker_id"
    ],
    "type": "object"
  },
  "risk_flags": [
    "arbitrary_network_egress",
    "freeform_input_surface"
  ]
}
Dispute this classification
list_competitor_scans read Low none No explicit safeguard hints detected.
Schema & evidence
{
  "annotations": {
    "openWorldHint": false,
    "readOnlyHint": true
  },
  "capabilities": [
    "read"
  ],
  "input_schema": {
    "properties": {
      "project_id": {
        "description": "Only the scans of this project: the UUID of a project of the account (call list_projects). Omitted, every project.",
        "format": "uuid",
        "type": "string"
      }
    },
    "type": "object"
  },
  "risk_flags": []
}
Dispute this classification
get_competitor_scan read Low none No explicit safeguard hints detected.
Schema & evidence
{
  "annotations": {
    "openWorldHint": false,
    "readOnlyHint": true
  },
  "capabilities": [
    "read"
  ],
  "input_schema": {
    "properties": {
      "competitor_scan_id": {
        "description": "The UUID of the competitor scan: call list_competitor_scans to find it.",
        "format": "uuid",
        "type": "string"
      }
    },
    "required": [
      "competitor_scan_id"
    ],
    "type": "object"
  },
  "risk_flags": []
}
Dispute this classification
create_competitor_scan write Medium none No explicit safeguard hints detected.
Schema & evidence
{
  "annotations": {
    "destructiveHint": false,
    "idempotentHint": false,
    "openWorldHint": false,
    "readOnlyHint": false
  },
  "capabilities": [
    "write"
  ],
  "input_schema": {
    "properties": {
      "category": {
        "description": "What qualifies each company in the questions, for example \"welding equipment manufacturer\".",
        "type": "string"
      },
      "country": {
        "description": "The market the questions name, as an ISO 3166-1 alpha-2 code (\"US\"). Omitted, the questions name no country.",
        "type": "string"
      },
      "engine": {
        "description": "The engine asked, ChatGPT by default. One per scan.",
        "enum": [
          "chatgpt",
          "claude",
          "gemini",
          "perplexity",
          "mistral",
          "grok"
        ],
        "type": "string"
      },
      "language": {
        "description": "The language the questions are asked in, for example \"en\". Omitted, the canonical language of the project.",
        "type": "string"
      },
      "project_id": {
        "description": "UUID of the project the scan belongs to: call list_projects to find it. Its brand is the one the list answers \"you are not there\" about.",
        "format": "uuid",
        "type": "string"
      },
      "subjects": {
        "description": "The basket: 3 to 5 companies of the same market.",
        "items": {
          "properties": {
            "name": {
              "description": "The company as the market names it, for example \"Lincoln Electric\".",
              "type": "string"
            },
            "website": {
              "description": "Its site, for example \"lincolnelectric.com\". Required: it is what identifies the company exactly.",
              "type": "string"
            }
          },
          "required": [
            "name",
            "website"
          ],
          "type": "object"
        },
        "maxItems": 5,
        "minItems": 3,
        "type": "array"
      },
      "title": {
        "description": "A name for the scan. Omitted, the category serves.",
        "type": "string"
      },
      "usage": {
        "description": "What buyers use it for, for example \"hobby welding\". Omitted, the category serves.",
        "type": "string"
      }
    },
    "required": [
      "project_id",
      "subjects",
      "category"
    ],
    "type": "object"
  },
  "risk_flags": []
}
Dispute this classification
start_competitor_scan undetermined Low none No explicit safeguard hints detected.
Schema & evidence
{
  "annotations": {
    "destructiveHint": false,
    "idempotentHint": true,
    "openWorldHint": false,
    "readOnlyHint": false
  },
  "capabilities": [
    "undetermined"
  ],
  "input_schema": {
    "properties": {
      "competitor_scan_id": {
        "description": "The UUID of the competitor scan: call list_competitor_scans to find it.",
        "format": "uuid",
        "type": "string"
      }
    },
    "required": [
      "competitor_scan_id"
    ],
    "type": "object"
  },
  "risk_flags": []
}
Dispute this classification
update_competitor_scan write Medium none No explicit safeguard hints detected.
Schema & evidence
{
  "annotations": {
    "destructiveHint": false,
    "idempotentHint": true,
    "openWorldHint": false,
    "readOnlyHint": false
  },
  "capabilities": [
    "write"
  ],
  "input_schema": {
    "properties": {
      "competitor_scan_id": {
        "description": "The UUID of the competitor scan: call list_competitor_scans to find it.",
        "format": "uuid",
        "type": "string"
      },
      "rescan_cadence": {
        "description": "How often the scan runs again: \"monthly\", or null to stop it.",
        "enum": [
          "monthly",
          null
        ],
        "type": [
          "string",
          "null"
        ]
      }
    },
    "required": [
      "competitor_scan_id"
    ],
    "type": "object"
  },
  "risk_flags": []
}
Dispute this classification
list_sources read network Medium arbitrary network egress freeform input surface No explicit safeguard hints detected.
Schema & evidence
{
  "annotations": {
    "openWorldHint": false,
    "readOnlyHint": true
  },
  "capabilities": [
    "read",
    "network"
  ],
  "input_schema": {
    "properties": {
      "domain": {
        "description": "Keep only the domains containing this text, e.g. \"wikipedia\" or \".fr\".",
        "type": "string"
      },
      "engine": {
        "description": "Keep only the sources this engine has cited at least once.",
        "enum": [
          "chatgpt",
          "claude",
          "gemini",
          "perplexity",
          "mistral",
          "grok"
        ],
        "type": "string"
      },
      "page": {
        "description": "Page number, from 1.",
        "minimum": 1,
        "type": "integer"
      },
      "per_page": {
        "description": "Entries per page, 25 by default, 100 at most.",
        "maximum": 100,
        "minimum": 1,
        "type": "integer"
      },
      "project_id": {
        "description": "Only the sources surfaced by the trackers of this project: the UUID of a project of the account (call list_projects), or \"default\" for the trackers without a project. Use it to read the map of one brand when the account holds several. Omitted, the map covers every tracker of the account, which is what shows a source weighing on two of its markets at once. The AI Authority scale does not move with it: it stays computed across the whole map, so the figures of two projects compare.",
        "type": "string"
      },
      "sort": {
        "description": "Order of the page: \"aa_chatgpt\", \"aa_claude\", \"aa_gemini\", \"aa_perplexity\", \"aa_mistral\" or \"aa_grok\" for the ranking of one AI, which also keeps only the sources that AI cites; \"detections\" ranks across all AIs at once, \"engines\" by number of distinct engines, \"freshness\" by most recent detection, \"domain\" alphabetically. Defaults to \"detections\".",
        "enum": [
          "detections",
          "engines",
          "freshness",
          "domain",
          "aa_chatgpt",
          "aa_claude",
          "aa_gemini",
          "aa_perplexity",
          "aa_mistral",
          "aa_grok"
        ],
        "type": "string"
      }
    },
    "type": "object"
  },
  "risk_flags": [
    "arbitrary_network_egress",
    "freeform_input_surface"
  ]
}
Dispute this classification
get_source read Low none No explicit safeguard hints detected.
Schema & evidence
{
  "annotations": {
    "openWorldHint": false,
    "readOnlyHint": true
  },
  "capabilities": [
    "read"
  ],
  "input_schema": {
    "properties": {
      "source_id": {
        "description": "The UUID of the source: call list_sources to find it.",
        "format": "uuid",
        "type": "string"
      }
    },
    "required": [
      "source_id"
    ],
    "type": "object"
  },
  "risk_flags": []
}
Dispute this classification
get_account_settings read Low none No explicit safeguard hints detected.
Schema & evidence
{
  "annotations": {
    "openWorldHint": false,
    "readOnlyHint": true
  },
  "capabilities": [
    "read"
  ],
  "input_schema": {
    "properties": {},
    "type": "object"
  },
  "risk_flags": []
}
Dispute this classification
update_account_settings write Medium none No explicit safeguard hints detected.
Schema & evidence
{
  "annotations": {
    "destructiveHint": false,
    "idempotentHint": true,
    "openWorldHint": false,
    "readOnlyHint": false
  },
  "capabilities": [
    "write"
  ],
  "input_schema": {
    "properties": {
      "billing_address": {
        "description": "Postal address of the account, one string per line, like [\"12 Example Street\", \"75001 Paris\"]. The list replaces the previous address; [] or null clears it. Three lines at most, so the address block of an invoice stays readable.",
        "items": {
          "type": "string"
        },
        "maxItems": 3,
        "type": "array"
      },
      "billing_country": {
        "description": "Billing country, as an ISO 3166-1 alpha-2 code: \"FR\", \"US\", \"BR\". It decides the tax treatment of the next invoices, so it is the country of the entity being billed, not where the user happens to be.",
        "type": "string"
      },
      "intra_eu_vat_number": {
        "description": "Intra-EU VAT number, for an account billed in an EU member state: the two-letter country code followed by the national number, like \"FR12345678901\". It goes on the invoices of the account.",
        "type": "string"
      },
      "language": {
        "description": "The language we write to this account in: emails, and the hosted payment page of a top-up.",
        "enum": [
          "en",
          "fr",
          "es",
          "de",
          "it",
          "pt"
        ],
        "type": "string"
      },
      "name": {
        "description": "Legal name of the account, the one printed on its invoices.",
        "type": "string"
      },
      "timezone": {
        "description": "The time zone the hours of the account are shown in, as an IANA identifier: \"Europe/Paris\", \"America/New_York\", \"UTC\".",
        "type": "string"
      }
    },
    "type": "object"
  },
  "risk_flags": []
}
Dispute this classification
get_credits read financial Low none No explicit safeguard hints detected.
Schema & evidence
{
  "annotations": {
    "openWorldHint": false,
    "readOnlyHint": true
  },
  "capabilities": [
    "read",
    "financial"
  ],
  "input_schema": {
    "properties": {},
    "type": "object"
  },
  "risk_flags": []
}
Dispute this classification
get_usage read Low none Safeguards hinted in metadata.
Schema & evidence
{
  "annotations": {
    "openWorldHint": false,
    "readOnlyHint": true
  },
  "capabilities": [
    "read"
  ],
  "input_schema": {
    "properties": {
      "month": {
        "description": "A single month, YYYY-MM. Omitted: every month the account has entries for.",
        "pattern": "^\\d{4}-\\d{2}$",
        "type": "string"
      },
      "page": {
        "minimum": 1,
        "type": "integer"
      },
      "per_page": {
        "maximum": 100,
        "minimum": 1,
        "type": "integer"
      },
      "type": {
        "description": "Which entries to return: all (default), in (top-ups and adjustments), out (spend).",
        "enum": [
          "all",
          "in",
          "out"
        ],
        "type": "string"
      }
    },
    "type": "object"
  },
  "risk_flags": []
}
Dispute this classification
topup_credits write financial High financial transaction No explicit safeguard hints detected.
Schema & evidence
{
  "annotations": {
    "destructiveHint": false,
    "idempotentHint": false,
    "openWorldHint": false,
    "readOnlyHint": false
  },
  "capabilities": [
    "write",
    "financial"
  ],
  "input_schema": {
    "properties": {
      "amount": {
        "description": "Credits to buy, in MAJOR units of the wallet currency: what a person says. 50 means 50.00, and 12.5 means 12.50. Use this one when the user names the amount, exactly as they said it. Minimum 10.00.",
        "exclusiveMinimum": 0,
        "type": "number"
      },
      "amount_minor": {
        "description": "Credits to buy, in MINOR units of the wallet currency: 5000 means 50.00. Use this one when you compute the amount from the cost grid, which is in minor units too. Minimum 1000.",
        "exclusiveMinimum": 0,
        "type": "integer"
      }
    },
    "type": "object"
  },
  "risk_flags": [
    "financial_transaction"
  ]
}
Dispute this classification
contact_support write Medium none No explicit safeguard hints detected.
Schema & evidence
{
  "annotations": {
    "destructiveHint": false,
    "idempotentHint": false,
    "openWorldHint": false,
    "readOnlyHint": false
  },
  "capabilities": [
    "write"
  ],
  "input_schema": {
    "properties": {
      "kind": {
        "description": "What this message is: sorts it on arrival.",
        "enum": [
          "problem",
          "suggestion",
          "question"
        ],
        "type": "string"
      },
      "message": {
        "description": "What you want to tell the support team, in the words of the user when they dictated it. Include what you tried and what happened.",
        "type": "string"
      },
      "subject": {
        "description": "Title of the thread. Derived from the message when omitted; ignored when replying.",
        "type": "string"
      },
      "thread_id": {
        "description": "Reply to this thread instead of opening a new one: call list_support_threads to find it.",
        "format": "uuid",
        "type": "string"
      }
    },
    "required": [
      "message"
    ],
    "type": "object"
  },
  "risk_flags": []
}
Dispute this classification
list_support_threads read Low none No explicit safeguard hints detected.
Schema & evidence
{
  "annotations": {
    "openWorldHint": false,
    "readOnlyHint": true
  },
  "capabilities": [
    "read"
  ],
  "input_schema": {
    "properties": {},
    "type": "object"
  },
  "risk_flags": []
}
Dispute this classification
get_support_thread read Low none No explicit safeguard hints detected.
Schema & evidence
{
  "annotations": {
    "openWorldHint": false,
    "readOnlyHint": true
  },
  "capabilities": [
    "read"
  ],
  "input_schema": {
    "properties": {
      "thread_id": {
        "description": "The UUID of the support thread: call list_support_threads to find it.",
        "format": "uuid",
        "type": "string"
      }
    },
    "required": [
      "thread_id"
    ],
    "type": "object"
  },
  "risk_flags": []
}
Dispute this classification
Write-action governance
Governance status
Warning
Safe to publish
Auth boundary
oauth_or_auth_required
Blast radius
Medium
High-risk tools
1
Confirmation signals
update_project_canon, set_link_targets, tick_surface_checklist, convert_surface_to_corroboration, create_corroboration, convert_corroboration_to_surface, create_logbook_entry, create_quest, restore_keyword_discovery, topup_credits
Safeguard count
9

Status detail: 1 high-risk tool(s), 5 destructive tool(s); auth boundary is oauth or auth required with 9 safeguard(s) and 10 confirmation signal(s).

ToolRiskFlagsSafeguards
topup_credits High financial transaction no
Recommended runtime policy
Recommended runtime policy
Allow with approval
Default policy stance (medium risk ceiling, write actions require approval, no OAuth requirement). Answers "what may an agent do right now" -- a separate question from production readiness, which answers "how suitable is this server for adoption." Customize via policy export.

No policy blockers under the default policy stance.

Action-controls diff
Snapshot changed
yes
Disabled-by-default candidates
none
New actions
ActionRiskFlags
create_competitor_scanMediumnone
get_competitor_scanLownone
list_competitor_scansLownone
start_competitor_scanLownone
update_competitor_scanMediumnone
Changed actions
ActionChange typesRisk
No materially changed actions.
Critical alerts
High/critical-severity alerts
1
Production verdicts degrade quickly when high or critical-severity alerts are active.

Compatibility

Client readiness verdicts

Client compatibility only means the server shape can work with a client. Production trust decision and write-action publishing are evaluated separately so a client-compatible server can still be blocked for production.

Client compatibility: ChatGPT
Not client-compatible
The tool surface is not limited to search/fetch-style read tools.; This client profile expects a read/search-only tool surface, but write, delete, or exec-capable tools are present.; Not yet safe for company-knowledge use: requires a search/fetch-only surface with no export, bulk, mutating, or high-blast-radius exposure.; Not yet safe for the Messages API remote MCP path: requires OAuth, a compatible connector profile, and no pending connector-refresh risk.; Transport compliance failed or did not complete successfully.
Confidence: high (100.0)
Evidence provenance
Winner: live_validation
Supporting sources: live_validation, history, server_card
Disagreements: none
  • initializeOK
  • tools_listOK
  • transport_compliance_probeWarning
  • step_up_auth_probeOK
  • connector_replay_probeWarning — Frozen tool snapshots must survive refresh.
  • request_association_probeMissing — Roots, sampling, and elicitation should stay request-scoped.
Client compatibility: Claude
Not client-compatible
The tool surface is not limited to search/fetch-style read tools.; This client profile expects a read/search-only tool surface, but write, delete, or exec-capable tools are present.; Not yet safe for company-knowledge use: requires a search/fetch-only surface with no export, bulk, mutating, or high-blast-radius exposure.; Not yet safe for the Messages API remote MCP path: requires OAuth, a compatible connector profile, and no pending connector-refresh risk.; Transport compliance failed or did not complete successfully.
Confidence: high (100.0)
Evidence provenance
Winner: live_validation
Supporting sources: live_validation, history, server_card
Disagreements: none
  • initializeOK
  • tools_listOK
  • transport_compliance_probeWarning
Write-action publishing
Publishing blocked
action_safety_probe is in warning -- the flagged risk has not been confirmed safe. Active alert(s) affecting production readiness: Tool snapshot changed.
Confidence: high (100.0)
Evidence provenance
Winner: live_validation
Supporting sources: live_validation, history
Disagreements: none
  • action_safety_probeWarning
Snapshot churn risk
Medium
The live tool surface changed between recent validations.
Confidence: high (100.0)
Evidence provenance
Winner: history
Supporting sources: history, live_validation
Disagreements: none
  • tool_snapshot_probeWarning
  • connector_replay_probeWarning
Client readiness gate details
ChatGPT custom connector
Not client-compatible
The tool surface is not limited to search/fetch-style read tools.; This client profile expects a read/search-only tool surface, but write, delete, or exec-capable tools are present.; Not yet safe for company-knowledge use: requires a search/fetch-only surface with no export, bulk, mutating, or high-blast-radius exposure.; Not yet safe for the Messages API remote MCP path: requires OAuth, a compatible connector profile, and no pending connector-refresh risk.; Transport compliance failed or did not complete successfully.
Remediation checklist
  • Limit the exposed surface to search/fetch-style read tools.
  • Remove or isolate write, delete, and exec-capable tools before using this read/search-only client profile.
  • Remove export, bulk, mutating, and high-blast-radius exposure before certifying company-knowledge use.
  • Satisfy OAuth, compatibility, and connector-refresh requirements before using the Messages API remote MCP path.
  • Resolve transport compliance issues before wider client rollout.
Claude remote MCP
Not client-compatible
The tool surface is not limited to search/fetch-style read tools.; This client profile expects a read/search-only tool surface, but write, delete, or exec-capable tools are present.; Not yet safe for company-knowledge use: requires a search/fetch-only surface with no export, bulk, mutating, or high-blast-radius exposure.; Not yet safe for the Messages API remote MCP path: requires OAuth, a compatible connector profile, and no pending connector-refresh risk.; Transport compliance failed or did not complete successfully.
Remediation checklist
  • Limit the exposed surface to search/fetch-style read tools.
  • Remove or isolate write, delete, and exec-capable tools before using this read/search-only client profile.
  • Remove export, bulk, mutating, and high-blast-radius exposure before certifying company-knowledge use.
  • Satisfy OAuth, compatibility, and connector-refresh requirements before using the Messages API remote MCP path.
  • Resolve transport compliance issues before wider client rollout.
Write-safe publishing
Blocked
action_safety_probe is in warning.
Remediation checklist
  • Confirm the flagged action-safety risk before treating this as write-safe.
Verdict traces
Production verdict
Safe for evaluation
The server is suitable for evaluation, but remaining gaps should be resolved before broad production use.
Confidence: high (100.0)
Winning source: live_validation
Triggering alerts
  • instruction_tool_reference_mismatch • low • Server instructions name unavailable tools
  • tool_snapshot_changed • high • Tool snapshot changed
Client verdict trace table
VerdictStatusChecksWinning sourceConflicts
openai_connectors Not client-compatible initialize, tools_list, transport_compliance_probe, step_up_auth_probe, connector_replay_probe, request_association_probe live_validation none
claude_desktop Not client-compatible initialize, tools_list, transport_compliance_probe live_validation none
unsafe_for_write_actions Publishing blocked action_safety_probe live_validation none
snapshot_churn_risk Medium tool_snapshot_probe, connector_replay_probe history none
Publishability policy profiles
ChatGPT custom connector publishability policy
Policy blocked
The tool surface is not limited to search/fetch-style read tools.; This client profile expects a read/search-only tool surface, but write, delete, or exec-capable tools are present.; Not yet safe for company-knowledge use: requires a search/fetch-only surface with no export, bulk, mutating, or high-blast-radius exposure.; Not yet safe for the Messages API remote MCP path: requires OAuth, a compatible connector profile, and no pending connector-refresh risk.; Transport compliance failed or did not complete successfully. Technical compatibility is evaluated separately from this publishability policy.
  • Search Fetch Only: No
  • Write Actions Present: Yes
  • Oauth Configured: Yes
  • Admin Refresh Required: No
  • Safe For Company Knowledge: No
  • Safe For Messages Api Remote Mcp: No
Claude remote MCP publishability policy
Policy blocked
The tool surface is not limited to search/fetch-style read tools.; This client profile expects a read/search-only tool surface, but write, delete, or exec-capable tools are present.; Not yet safe for company-knowledge use: requires a search/fetch-only surface with no export, bulk, mutating, or high-blast-radius exposure.; Not yet safe for the Messages API remote MCP path: requires OAuth, a compatible connector profile, and no pending connector-refresh risk.; Transport compliance failed or did not complete successfully. Technical compatibility is evaluated separately from this publishability policy.
  • Search Fetch Only: No
  • Write Actions Present: Yes
  • Oauth Configured: Yes
  • Admin Refresh Required: No
  • Safe For Company Knowledge: No
  • Safe For Messages Api Remote Mcp: No
Compatibility fixtures
ChatGPT custom connector fixture
Passes
Live checks line up with current ChatGPT connector assumptions.
  • remote_http_endpoint: Passes
  • oauth_discovery: Passes
  • frozen_tool_snapshot_refresh: Passes
  • request_association: Not Assessed
Anthropic remote MCP fixture
Degraded
Remote MCP transport and discovery assumptions are satisfied.
  • remote_transport: Passes
  • tool_discovery: Passes
  • auth_connect: Passes
  • safe_write_review: Degraded
Recommended for
Smithery
Smithery is marked compatible with score 80.
Generic Streamable HTTP
Generic Streamable HTTP is marked compatible with score 100.

Evidence

Current trust snapshot
Snapshot ID
trustsnap_d98e22cf57788997
Use this ID to compare server page, report, policy, MCP, homepage, ranking, and shortlist surfaces.
Trust evaluated
Aug 15, 2026 03:37:40 PM UTC
Evidence revision: 8ffb3f6fa37a21e996089991 • materialization: complete
Last validated
Aug 15, 2026 03:56:00 AM UTC
Age: 11.69h • evidence age tier: Verified in last 24h • display score: 68.23

Canonical machine links

Evidence confidence
Confidence score
100.0
Based on 20 recent validations, 18 captured checks, and validation age of 11.7 hours.
Live checks captured
18
More direct checks increase trust in the current verdict.
Validation age
11.7h
Lower age means fresher evidence.
Latest validation evidence
Latest summary
Healthy
Validation profile
remote_mcp
Started
Aug 15, 2026 03:55:56 AM UTC
Latency
4067.2 ms

Failures

  • openid_configuration Client error '404 Not Found' for url 'https://app.epovest.com/.well-known/openid-configuration' For more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404
  • server_card Client error '404 Not Found' for url 'https://mcp.epovest.com/.well-known/mcp/server-card.json' For more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404

Checks

CheckStatusLatencyEvidence
action_safety_probe Warning n/a 1 high-risk, 5 destructive, 10 egress-capable, 45 declared non-read-only, non-read capabilities: write, delete, financial tool(s); auth present; safeguards=9; confirmation=update project canon, set link targets, tick surface checklist, convert surface to corroboration, +6 more.
advanced_capabilities_probe Warning n/a Only 2 capability signal(s): prompts, resources.
connector_publishability_probe Warning n/a Publishability blockers: protocol version, session resume, transport compliance, connector replay, +3 more.
connector_replay_probe Warning n/a Backward compatible with additive changes; added tools=5, additive output changes=0.
determinism_probe OK 289.4 ms Check completed
initialize OK 343.8 ms Protocol 2025-03-26
instruction_tool_reference_probe Warning n/a Check completed
interactive_flow_probe OK n/a Check completed
oauth_authorization_server OK 456.6 ms authorization_endpoint, authorization_response_iss_parameter_supported, client_id_metadata_document_supported, code_challenge_methods_supported
oauth_protected_resource OK 365.6 ms 1 authorization server(s)
official_registry_probe Missing n/a Check completed
openid_configuration Error 332.6 ms Client error '404 Not Found' for url 'https://app.epovest.com/.well-known/openid-configuration' For more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404
probe_noise_resilience OK 398.2 ms Fetched https://mcp.epovest.com/robots.txt
prompt_get Missing n/a not advertised
prompts_list Auth Required 135.1 ms Client error '401 Unauthorized' for url 'https://mcp.epovest.com/mcp' For more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/401
protocol_version_probe Warning n/a Claims 2025-03-26; 2 release(s) behind 2025-11-25.
provenance_divergence_probe Not_Assessed n/a Check completed
request_association_probe Missing n/a No request-association capabilities were advertised.
resource_read Missing n/a not advertised
resources_list Auth Required 265.8 ms Client error '401 Unauthorized' for url 'https://mcp.epovest.com/mcp' For more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/401
schema_divergence_probe Missing n/a no server card tools
server_card Error 395.1 ms Client error '404 Not Found' for url 'https://mcp.epovest.com/.well-known/mcp/server-card.json' For more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404
session_resume_probe Warning n/a no session id
step_up_auth_probe OK n/a Scopes=read, write; broad scopes=write; step-up challenge hints present.
tool_snapshot_probe Warning n/a Check completed
tools_list OK 365.6 ms 66 tool(s) exposed
transport_compliance_probe Warning 93.7 ms Issues: missing session id, missing protocol header (bad protocol=400).
utility_coverage_probe OK 94.9 ms No completions evidence; no pagination evidence; tasks auth required.
Known versions
  • No versions recorded.
Public server reputation
Validation success 7d
1.0
Validation success 30d
1.0
Mean time to recover
n/a
Breaking diffs 30d
1
Registry drift frequency 30d
0
Snapshot changes 30d
1
Benchmark tasks
Benchmark taskStatusEvidence
Discover tools Passes
  • initializeOK
  • tools_listOK
Read-only fetch flow Degraded
  • resource_readMissing
  • read_only_tool_surfaceOK
OAuth-required connect Passes
  • oauth_protected_resourceOK
  • step_up_auth_probeOK
Safe write flow with confirmation Degraded
  • action_safety_probeWarning
Utility coverage
Probe status
OK
Completions
not detected
Completion probe target: none
Pagination
not detected
No nextCursor evidence.
Tasks
Auth Required
Advertised: no
Tool snapshot diff & changelog
Snapshot changed
yes
Added tools
create_competitor_scan get_competitor_scan list_competitor_scans start_competitor_scan update_competitor_scan
Removed tools
none
Required-argument changes
ToolAdded required argsRemoved required args
No required-argument changes detected.
Output-schema drift
ToolPrevious propertiesLatest properties
No output-schema drift detected.
Validation diff
Score delta
-1.56
Summary changed
no
Tool delta
5
Prompt delta
0
Auth mode changed
no
Write surface expanded
no
Protocol regressed
no
Registry drift changed
no

Regressed checks: connector_replay_probe, tool_snapshot_probe

Improved checks: none

Newly assessed dimensions: none

No longer assessed dimensions: none

ComponentPreviousLatestDelta
backward_compatibility_score4.03.0-1.0
connector_publishability_score2.01.0-1.0
official_registry_presence_score3.02.0-1.0
Registry & provenance divergence
Probe status
Not_Assessed
Assessment
Not assessed
probe_not_assessed
Cross-registry alias disagreements
Warning registry_source homepage registry_identifier
Active alerts
  • Server instructions name unavailable tools (low)
    Initialize instructions reference tools not present in tools/list: returns
  • Tool snapshot changed (high)
    Tools were added, removed, or materially changed between the latest two validations.
Aliases & registry graph
IdentifierSourceCanonicalIdentity evidenceScore
Epovest/mcp-server glama_registry yes canonical 68.2
github-epovest/mcp-server github_topic_registry no repo_slug n/a
Alias consolidation

Strong alias identity requires matching remote URL, server-card URL, repository slug, or explicit registry cross-reference; shared provider namespace alone is not identity.

Canonical identifier
Epovest/mcp-server
Duplicate aliases
1
Registry sources
github_topic_registry glama_registry
Directory listings
none
Source disagreements
FieldWhat differsObserved values
Registry source Multiple registries or registry sync paths claim this same canonical server. github_topic_registry glama_registry
Homepage Registry entries disagree on the primary homepage for this server. https://epovest.com https://glama.ai/mcp/servers/df7w4wyfi0
Registry identifier Different registry-specific identifiers resolve to the same canonical server record here. github_topic_registry:Epovest/mcp-server glama_registry:df7w4wyfi0

Fix it

Why this score?
Access & Protocol
33/44
Connectivity, auth, and transport expectations for common clients.
Interface Quality
35/56
How well the tool/resource interface communicates and behaves under automation.
Security Posture
27/36
How safely the exposed tool surface handles destructive actions, egress, execution, secrets, and risky inputs.
Reliability & Trust
22/24
Operational stability, consistency, and trustworthiness over time.
Discovery & Governance
11/28
How well the server is documented, listed, and governed in public registries.
Adoption & Market
3/8
Adoption clues and public evidence that the server is intended for external use.
Algorithmic score breakdown
Auth Operability
4/4
Measures whether auth discovery and protected access behave predictably for clients.
Error Contract Quality
1/4
Grades machine-readable error structure, status alignment, and remediation hints.
Rate-Limit Semantics
2/4
Checks whether quota/throttle responses are deterministic and automation-friendly.
Schema Completeness
3/4
Completeness of tool descriptions, parameter docs, examples, and schema shape.
Backward Compatibility
3/4
Stability score across tool schema/name drift relative to prior validations.
SLO Health
3/4
Availability, latency, and burst-failure profile across recent validation history.
Security Hygiene
4/4
HTTPS posture, endpoint hygiene, and response-surface hardening checks.
Task Success
4/4
Can an agent reliably initialize, enumerate tools, and execute core MCP flows?
Trust Confidence
4/4
Confidence-adjusted reliability score that penalizes low evidence volume.
Abuse/Noise Resilience
4/4
How well the server preserves core behavior in the presence of noisy traffic patterns.
Prompt Contract
2/4
Quality of prompt metadata, argument shape, and prompt discoverability for clients.
Resource Contract
2/4
How completely resources and resource templates describe URIs, types, and usage shape.
Discovery Metadata
2/4
Homepage, docs, icon, repository, support, and license coverage for directory consumers.
Registry Consistency
2/4
Agreement between stored registry metadata, live server-card data, and current validation output.
Installability
4/4
How cleanly a real client can connect, initialize, enumerate tools, and proceed through auth.
Session Semantics
4/4
Determinism and state behavior across repeated MCP calls, including sticky-session surprises.
Tool Surface Design
3/4
Naming clarity, schema ergonomics, and parameter complexity across the tool surface.
Result Shape Stability
3/4
Stability of declared output schemas across validations, with penalties for drift or missing shapes.
OAuth Interop
4/4
Depth and client compatibility of OAuth/OIDC metadata beyond the minimal protected-resource check.
Recovery Semantics
1/4
Whether failures include actionable machine-readable next steps such as retry or upgrade guidance.
Maintenance Signal
3/4
Versioning, update recency, and historical validation cadence that indicate active stewardship.
Adoption Signal
2/4
Directory presence and distribution clues that suggest the server is intended for external use.
Freshness Confidence
4/4
Confidence that recent validations are current enough and dense enough to trust operationally.
Transport Fidelity
4/4
Whether declared transport metadata matches the observed endpoint behavior and response formats.
Spec Recency
2/4
How close the server’s claimed MCP protocol version is to the latest known public revision.
Session Resume
3/4
Whether Streamable HTTP session identifiers and resumed requests behave cleanly for real clients.
Step-Up Auth
4/4
Whether OAuth metadata and WWW-Authenticate challenges support granular, incremental consent instead of broad upfront scopes.
Transport Compliance
2/4
Checks session headers, protocol-version enforcement, session teardown, and expired-session behavior.
Utility Coverage
1/4
Signals support for completions, pagination, and task-oriented utility surfaces that larger clients increasingly expect.
Advanced Capability Coverage
1/4
Coverage of newer MCP surfaces like roots, sampling, elicitation, structured output, and related metadata.
Connector Publishability
1/4
How ready the server looks for client catalogs and managed connector programs.
Tool Snapshot Churn
4/4
Stability of the tool surface across recent validations, including add/remove and output-shape drift.
Connector Replay
4/4
Whether a previously published frozen connector snapshot would remain backward compatible after the latest tool refresh.
Request Association
0/4
Whether roots, sampling, and elicitation appear tied to active client requests instead of arriving unsolicited on idle sessions.
Interactive Flow Safety
3/4
Whether prompts and docs steer users toward safe auth flows instead of pasting secrets directly.
Action Safety
2/4
Risk-weighted view of destructive, exec, egress, and confirmation semantics across the tool surface.
Official Registry Presence
2/4
Whether the server appears directly or indirectly in the official MCP registry.
Safety Transparency
2/4
Clarity of docs, auth disclosure, support links, and other trust signals visible to integrators.
Tool Capability Clarity
4/4
How clearly the tool surface communicates whether each action reads, writes, deletes, executes, or exports data.
Destructive Operation Safety
3/4
Penalizes delete/revoke/destroy style tools unless auth and safeguards reduce blast radius.
Egress / SSRF Resilience
2/4
Assesses arbitrary URL fetch, crawl, webhook, and remote-request exposure on the tool surface.
Execution / Sandbox Safety
4/4
Evaluates shell, code, script, and command-execution exposure and whether that surface appears contained.
Data Exfiltration Resilience
3/4
Assesses export, dump, backup, and bulk-read behavior against the surrounding auth and safeguard signals.
Least Privilege Scope
2/4
Rewards scoped auth metadata and penalizes broad or missing scopes around privileged tools.
Secret Handling Hygiene
3/4
Assesses secret-bearing tools, token leakage risk, and whether the public surface avoids obvious secret exposure.
Supply Chain Signal
0/4
Public metadata signal for repository, changelog, license, versioning, and recency that supports supply-chain trust.
Input Sanitization Safety
3/4
Penalizes risky freeform string inputs when schemas do not constrain URLs, code, paths, queries, or templates.
Tool Namespace Clarity
4/4
Measures naming uniqueness and ambiguity across the tool namespace to reduce collision and confusion risk.

1 component(s) not assessed for this run: Provenance Divergence

Experimental candidate components
Personal Data Exposure
8.5
Experimental candidate, weight 0. Export and bulk-access evidence only; no impact on totals, verdicts, rankings, or gates.
Actionable remediation
SeverityRemediationWhy it mattersRecommended action
High Add confirmation and dry-run semantics for risky actions High-risk write, delete, exec, or egress tools should communicate safeguards clearly. Add an explicit confirm/dry-run parameter or two-step confirmation flow to write, delete, exec, and egress-capable tools before they can make destructive changes.
Playbook
  • For each high-risk tool (delete, exec, or network-egress capable), add a `confirm`/`dry_run` parameter or a two-step confirmation flow.
  • Document the safeguard in the tool's description so clients and agents know confirmation is required before execution.
  • Revalidate and confirm `action_safety_probe` reports the safeguard as detected.
High Align session and protocol behavior with Streamable HTTP expectations Clients increasingly rely on MCP-Protocol-Version, session teardown, and expired-session semantics. Align MCP-Protocol-Version, MCP-Session-Id, DELETE teardown, and expired-session handling with the transport spec.
Playbook
  • Return `Mcp-Session-Id` and `Mcp-Protocol-Version` headers consistently on streamable HTTP responses.
  • Honor `DELETE` session teardown and return `404` when a deleted session is reused.
  • Reject invalid protocol-version headers with `400 Bad Request`.
High Keep connector refreshes backward compatible Managed connector clients freeze tool snapshots, so removed tools, new required args, and breaking output changes can break published integrations after refresh. Avoid removing tools, adding new required arguments, or changing outputSchema for tools already published to connector directories without a version bump.
Playbook
  • Avoid removing tools or adding new required arguments to existing tools without a major version bump.
  • Avoid breaking changes to `outputSchema` for tools already published to connector directories.
  • This check reads `no_historical_snapshot` on a server's first validation run -- that is expected, not itself a defect, and resolves after a second run.
High Publish a complete server card Missing or incomplete server-card metadata weakens discovery, documentation, and trust signals. Serve /.well-known/mcp/server-card.json and include tools, prompts/resources, homepage, and support links.
Playbook
  • Publish `/.well-known/mcp/server-card.json`.
  • Include homepage, repository, support, tools, prompts/resources, and auth metadata.
  • Revalidate the server after publishing the card.
High Respond to tool snapshot changed Tools were added, removed, or materially changed between the latest two validations. Publish a first-class changelog for tool additions, removals, and breaking schema changes.
Playbook
  • Review the tool snapshot diff for adds, removals, required-arg changes, and output-schema drift.
  • Publish a changelog before managed connector clients refresh their frozen tool snapshots.
  • Revalidate after the changelog and connector metadata are in sync.
Medium Adopt a current MCP protocol revision Older protocol revisions reduce compatibility with newer clients and registry programs. Advertise a current MCP protocol revision (2025-06-18 or later) in both the initialize response and the MCP-Protocol-Version header.
Playbook
  • Update the server's advertised protocol version to a current MCP revision (2025-06-18 or later).
  • Return the negotiated version consistently in both the `initialize` response and the `MCP-Protocol-Version` header.
  • Revalidate and confirm `protocol_version_probe` reports `ok`.
Medium Close connector-publishing gaps Connector catalogs care about protocol recency, session behavior, auth clarity, and tool-surface stability. Resolve every blocker named by connector_publishability_probe, then rerun it before submitting or refreshing a connector listing.
Playbook
  • Review the blockers and failed criteria recorded by connector_publishability_probe.
  • Correct the identified transport, authentication, server-card, or tool-stability gaps.
  • Revalidate and require the probe to report no blockers before publishing the connector.
Medium Publish OpenID configuration OIDC metadata improves token validation and client compatibility. Expose /.well-known/openid-configuration with issuer, jwks_uri, and supported grants.
Playbook
  • Serve `/.well-known/openid-configuration` with `issuer`, `jwks_uri`, `authorization_endpoint`, and `token_endpoint`.
  • List supported grant types in `grant_types_supported` and scopes in `scopes_supported`.
  • Revalidate and confirm the `openid_configuration` check returns `ok`.
Medium Raise Adoption & Market score Adoption clues and public evidence that the server is intended for external use. Increase external documentation and directory coverage so users can discover and evaluate the server.
Medium Reduce tool-surface churn Frequent add/remove or output-shape drift makes published connectors and cached tool snapshots brittle. Keep tool names, required arguments, and output schemas stable between deploys, and publish a changelog entry when they must change.
Playbook
  • Avoid changing tool names, required arguments, or output schemas between deploys unless the change is intentional.
  • Publish a changelog entry when the tool surface changes so cached or frozen client snapshots can be reconciled.
  • This check compares against the previous run, so it needs a second validation before it can report a stable baseline.
Medium Repair prompts/list or stop advertising prompts Prompt metadata should either work live or be removed from the advertised capability set. Only advertise prompts if prompts/list works and prompt arguments are documented.
Playbook
  • Only advertise prompts that are actually accessible.
  • Add prompt descriptions and argument docs.
  • Run a live `prompts/list` check after any prompt changes.
Medium Repair resources/list or stop advertising resources Resource metadata should either work live or be removed from the advertised capability set. Only advertise resources if resources/list works and resources expose stable URIs/types.
Playbook
  • Only advertise resources with stable URIs and read semantics.
  • Add MIME/type hints where possible.
  • Run a live `resources/list` and `resources/read` check after updates.
Medium Support resumable HTTP sessions cleanly Modern MCP clients increasingly expect resumable session behavior on streamable HTTP transports. Persist session state keyed by Mcp-Session-Id and honor Last-Event-ID on GET reconnects so clients can resume a dropped Streamable HTTP session.
Playbook
  • Persist session state keyed by `Mcp-Session-Id` so a client can reconnect after a dropped connection.
  • Honor `Last-Event-ID` on GET reconnects to replay missed SSE events instead of erroring.
  • Revalidate and confirm `session_resume_probe` no longer returns `warning`.
Low Publish newer MCP capability signals Roots, sampling, elicitation, structured outputs, and related metadata improve client understanding and ranking. Advertise only the advanced capabilities (roots, sampling, elicitation) you have actually implemented end to end in the initialize capabilities object.
Playbook
  • Add the capabilities you actually support (`roots`, `sampling`, `elicitation`) to the `capabilities` object returned from `initialize`.
  • Only advertise a capability once the corresponding request/response flow is implemented end to end.
  • Revalidate and confirm `advanced_capabilities_probe` reflects the updated capability set.
Low Publish or reconcile the server in the official MCP registry Official registry presence improves discovery confidence and cross-source consistency. Create or update the official MCP registry entry with the canonical MCP endpoint and matching repository metadata, then rerun official_registry_probe.
Playbook
  • Locate or create the canonical entry in the official MCP registry.
  • Publish the live MCP endpoint and reconcile its repository and homepage metadata.
  • Revalidate and confirm official_registry_probe recognizes the reconciled entry.
Low Remove stale tool names from server instructions Initialize instructions explicitly reference tools that tools/list does not expose. Update initialize instructions so every explicitly named tool exists in tools/list.
Playbook
  • Compare the initialize result's instructions field with the current tools/list names.
  • Rename the explicit reference or restore the missing tool.
  • Revalidate and confirm instruction_tool_reference_probe reports ok.
Point loss breakdown
ComponentCurrentPoints missing
Request Association 0/4 -4.0
Supply Chain Signal 0/4 -4.0
Utility Coverage 1/4 -3.0
Recovery Semantics 1/4 -3.0
Error Contract Quality 1/4 -3.0
Connector Publishability 1/4 -3.0
Advanced Capability Coverage 1/4 -3.0
Transport Compliance 2/4 -2.0
Spec Recency 2/4 -2.0
Safety Transparency 2/4 -2.0
Resource Contract 2/4 -2.0
Registry Consistency 2/4 -2.0
Technical compatibility profiles

These scores measure technical client compatibility only. Client publishability and production readiness are evaluated separately against policy, transport, and write-surface blockers.

OpenAI Connectors
100.0
Technically compatible (9 of 9 requirements met)
No technical compatibility criteria are currently unmet.
Connector URL: https://mcp.epovest.com/mcp
# Complete OAuth in the client when prompted.
# Server: Epovest/mcp-server
Claude Desktop
100.0
Technically compatible (6 of 6 requirements met)
No technical compatibility criteria are currently unmet.
{
  "mcpServers": {
    "mcp-server": {
      "command": "npx",
      "args": ["mcp-remote", "https://mcp.epovest.com/mcp"]
    }
  }
}
Smithery
80.0
Technically compatible (4 of 5 requirements met)
Machine-readable failure semantics should be present.
smithery mcp add "https://mcp.epovest.com/mcp"
Generic Streamable HTTP
100.0
Technically compatible (6 of 6 requirements met)
No technical compatibility criteria are currently unmet.
curl -sS https://mcp.epovest.com/mcp -H 'content-type: application/json' -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-03-26","capabilities":{},"clientInfo":{"name":"mcp-verify","version":"0.1.0"}}}'

Governance

MCP TrustOps

TrustOps turns this report into operational controls: validation targets and SLAs, authenticated validation, semantic benchmarks, policy exports, alert subscriptions, badges, cost/compliance metadata, and runtime routing. Fresh trusted index decisions stay separate from long-tail inventory so stale scores do not masquerade as current evidence.

Evidence age tier
Verified in last 24h
Policy evidence-age limit (a runtime constraint, distinct from the public 24h freshness window and from a plan's validation target/SLA): 168.0h • confidence-weighted score (display score discounted for evidence age and confidence -- an internal TrustOps input, not the public score): 68.2 • score suppressed after the 30-day display limit:
Policy exports
Formats: json, rego, yaml, github_action, gateway_config, client_report
Runtime routing
/v1/decide
Returns allowed tools, blocked tools, approval requirement, and reason.
Hosted runtime
Deploy trusted servers from GitHub with secrets, egress controls, releases, rollback, and audit events.
Authenticated validation
Premium publisher feature: paid authenticated runs verify scopes, write-action safeguards, and authorized tool execution.
Active trust badges
none
Semantic benchmarks
available
Templates cover GitHub, database, healthcare, web search, and CRM least-privilege jobs.
Supply chain
metadata signal
Deep scan checks are marked separately from public metadata signals.
Compliance metadata
Terms, privacy, SOC 2, HIPAA, GDPR, retention, deletion, and audit-log fields are tracked as enterprise metadata.
Alert subscription types
Status changes Score drops or recovers Evidence-age policy breach Validation schema drift OAuth or auth behavior changes Tool surface changes New or changed write tool Supply-chain signal changes Legal or compliance metadata changes
MCP Runtime hosting

Verify Hosted MCP turns a trusted server report into a managed remote MCP endpoint with GitHub deployment provenance, sandbox policy, encrypted secrets, release history, rollback, and audit/usage events.

Activation readiness
Trusted hosted runtimes require fresh validation, a passing server state, a remote endpoint, and a minimum score.
Minimum tier
TrustOps
Publisher claim plus paid TrustOps tier are required before secrets or releases can be created.
Hosted endpoint
/hosted/{namespace}/{name}/mcp
The endpoint enforces egress allowlists and records audit/usage events.
Blockers
score_below_hosting_threshold blocked_by_active_alerts unsafe_write_action_surface
DeploymentStatusEndpointRelease
No hosted runtime deployments yet.
Authenticated validation sessions

Public validation is free. Authenticated validation is paid and proves scoped behavior, write-action safeguards, and authenticated tool execution.

Latest profile
remote_mcp
Authenticated session used
Public score isolation
Preview endpoint
/v1/verify
CI preview endpoint
/v1/ci/preview
Install snippets
Openai Connectors
Connector URL: https://mcp.epovest.com/mcp
# Complete OAuth in the client when prompted.
# Server: Epovest/mcp-server
Claude Desktop
{
  "mcpServers": {
    "mcp-server": {
      "command": "npx",
      "args": ["mcp-remote", "https://mcp.epovest.com/mcp"]
    }
  }
}
Smithery
smithery mcp add "https://mcp.epovest.com/mcp"
Generic Http
curl -sS https://mcp.epovest.com/mcp -H 'content-type: application/json' -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-03-26","capabilities":{},"clientInfo":{"name":"mcp-verify","version":"0.1.0"}}}'
Agent access & tool surface
Live server tools
list_trackers create_tracker update_tracker start_tracker survey_now pause_tracker archive_tracker list_projects
Showing 8 of 66 tools.
Observed from the latest live validation against https://mcp.epovest.com/mcp. This is the target server surface, not Verify's own inspection tools.
Live capability counts
66 tools • 0 prompts • 0 resources
Counts come from the latest tools/list, prompts/list, and resources/list checks.
Inspect with Verify
search fetch search_servers recommend_servers get_server_report compare_servers
Use Verify itself to search, recommend, compare, and fetch the full report for Epovest/mcp-server.
Direct machine links

History

Validation history
7 day score delta
n/a
30 day score delta
n/a
Recent healthy ratio
100%
Freshness
11.7h
TimestampStatusScoreLatencyTools
Aug 15, 2026 03:56:00 AM UTC Healthy 68.2 4067.2 ms 66
Aug 14, 2026 03:54:28 PM UTC Healthy 69.8 3920.5 ms 61
Aug 14, 2026 03:22:49 AM UTC Healthy 69.3 3439.7 ms 61
Aug 13, 2026 08:46:28 PM UTC Healthy 69.3 2619.4 ms 61
Aug 13, 2026 08:44:32 PM UTC Healthy 69.3 4435.0 ms 61
Aug 13, 2026 08:35:00 AM UTC Healthy 69.3 3474.6 ms 61
Aug 12, 2026 08:12:31 PM UTC Healthy 69.8 4058.4 ms 61
Aug 12, 2026 07:59:25 AM UTC Healthy 69.8 3159.3 ms 61
Aug 11, 2026 07:30:27 PM UTC Healthy 69.8 3903.8 ms 61
Aug 11, 2026 07:09:03 AM UTC Healthy 69.8 3764.9 ms 61
Validation timeline
ValidatedSummaryScoreProtocolAuth modeToolsHigh-risk toolsChanges
Aug 15, 2026 03:56:00 AM UTC Healthy 68.2 2025-03-26 oauth_supported 66 1 tool_snapshot_changed
Aug 14, 2026 03:54:28 PM UTC Healthy 69.8 2025-03-26 oauth_supported 61 1 none
Aug 14, 2026 03:22:49 AM UTC Healthy 69.3 2025-03-26 oauth_supported 61 1 none
Aug 13, 2026 08:46:28 PM UTC Healthy 69.3 2025-03-26 oauth_supported 61 1 none
Aug 13, 2026 08:44:32 PM UTC Healthy 69.3 2025-03-26 oauth_supported 61 1 none
Aug 13, 2026 08:35:00 AM UTC Healthy 69.3 2025-03-26 oauth_supported 61 1 none
Aug 12, 2026 08:12:31 PM UTC Healthy 69.8 2025-03-26 oauth_supported 61 1 none
Aug 12, 2026 07:59:25 AM UTC Healthy 69.8 2025-03-26 oauth_supported 61 1 none
Aug 11, 2026 07:30:27 PM UTC Healthy 69.8 2025-03-26 oauth_supported 61 1 none
Aug 11, 2026 07:09:03 AM UTC Healthy 69.8 2025-03-26 oauth_supported 61 1 none
Recent validation runs
Recent validation runs for this MCP server
StartedStatusSummaryLatencyChecks
Aug 15, 2026 03:55:56 AM UTC Completed Healthy 4067.2 ms action_safety_probe, advanced_capabilities_probe, connector_publishability_probe, connector_replay_probe, determinism_probe, initialize, instruction_tool_reference_probe, interactive_flow_probe, oauth_authorization_server, oauth_protected_resource, official_registry_probe, openid_configuration, probe_noise_resilience, prompt_get, prompts_list, protocol_version_probe, provenance_divergence_probe, request_association_probe, resource_read, resources_list, schema_divergence_probe, server_card, session_resume_probe, step_up_auth_probe, tool_snapshot_probe, tools_list, transport_compliance_probe, utility_coverage_probe
Aug 14, 2026 03:54:24 PM UTC Completed Healthy 3920.5 ms action_safety_probe, advanced_capabilities_probe, connector_publishability_probe, connector_replay_probe, determinism_probe, initialize, instruction_tool_reference_probe, interactive_flow_probe, oauth_authorization_server, oauth_protected_resource, official_registry_probe, openid_configuration, probe_noise_resilience, prompt_get, prompts_list, protocol_version_probe, provenance_divergence_probe, request_association_probe, resource_read, resources_list, schema_divergence_probe, server_card, session_resume_probe, step_up_auth_probe, tool_snapshot_probe, tools_list, transport_compliance_probe, utility_coverage_probe
Aug 14, 2026 03:22:45 AM UTC Completed Healthy 3439.7 ms action_safety_probe, advanced_capabilities_probe, connector_publishability_probe, connector_replay_probe, determinism_probe, initialize, instruction_tool_reference_probe, interactive_flow_probe, oauth_authorization_server, oauth_protected_resource, official_registry_probe, openid_configuration, probe_noise_resilience, prompt_get, prompts_list, protocol_version_probe, provenance_divergence_probe, request_association_probe, resource_read, resources_list, schema_divergence_probe, server_card, session_resume_probe, step_up_auth_probe, tool_snapshot_probe, tools_list, transport_compliance_probe, utility_coverage_probe
Aug 13, 2026 08:46:26 PM UTC Completed Healthy 2619.4 ms action_safety_probe, advanced_capabilities_probe, connector_publishability_probe, connector_replay_probe, determinism_probe, initialize, interactive_flow_probe, oauth_authorization_server, oauth_protected_resource, official_registry_probe, openid_configuration, probe_noise_resilience, prompt_get, prompts_list, protocol_version_probe, provenance_divergence_probe, request_association_probe, resource_read, resources_list, schema_divergence_probe, server_card, session_resume_probe, step_up_auth_probe, tool_snapshot_probe, tools_list, transport_compliance_probe, utility_coverage_probe
Aug 13, 2026 08:44:27 PM UTC Completed Healthy 4435.0 ms action_safety_probe, advanced_capabilities_probe, connector_publishability_probe, connector_replay_probe, determinism_probe, initialize, interactive_flow_probe, oauth_authorization_server, oauth_protected_resource, official_registry_probe, openid_configuration, probe_noise_resilience, prompt_get, prompts_list, protocol_version_probe, provenance_divergence_probe, request_association_probe, resource_read, resources_list, schema_divergence_probe, server_card, session_resume_probe, step_up_auth_probe, tool_snapshot_probe, tools_list, transport_compliance_probe, utility_coverage_probe
Aug 13, 2026 08:34:56 AM UTC Completed Healthy 3474.6 ms action_safety_probe, advanced_capabilities_probe, connector_publishability_probe, connector_replay_probe, determinism_probe, initialize, interactive_flow_probe, oauth_authorization_server, oauth_protected_resource, official_registry_probe, openid_configuration, probe_noise_resilience, prompt_get, prompts_list, protocol_version_probe, provenance_divergence_probe, request_association_probe, resource_read, resources_list, schema_divergence_probe, server_card, session_resume_probe, step_up_auth_probe, tool_snapshot_probe, tools_list, transport_compliance_probe, utility_coverage_probe
Aug 12, 2026 08:12:27 PM UTC Completed Healthy 4058.4 ms action_safety_probe, advanced_capabilities_probe, connector_publishability_probe, connector_replay_probe, determinism_probe, initialize, interactive_flow_probe, oauth_authorization_server, oauth_protected_resource, official_registry_probe, openid_configuration, probe_noise_resilience, prompt_get, prompts_list, protocol_version_probe, provenance_divergence_probe, request_association_probe, resource_read, resources_list, schema_divergence_probe, server_card, session_resume_probe, step_up_auth_probe, tool_snapshot_probe, tools_list, transport_compliance_probe, utility_coverage_probe
Aug 12, 2026 07:59:22 AM UTC Completed Healthy 3159.3 ms action_safety_probe, advanced_capabilities_probe, connector_publishability_probe, connector_replay_probe, determinism_probe, initialize, interactive_flow_probe, oauth_authorization_server, oauth_protected_resource, official_registry_probe, openid_configuration, probe_noise_resilience, prompt_get, prompts_list, protocol_version_probe, provenance_divergence_probe, request_association_probe, resource_read, resources_list, schema_divergence_probe, server_card, session_resume_probe, step_up_auth_probe, tool_snapshot_probe, tools_list, transport_compliance_probe, utility_coverage_probe
Aug 11, 2026 07:30:23 PM UTC Completed Healthy 3903.8 ms action_safety_probe, advanced_capabilities_probe, connector_publishability_probe, connector_replay_probe, determinism_probe, initialize, interactive_flow_probe, oauth_authorization_server, oauth_protected_resource, official_registry_probe, openid_configuration, probe_noise_resilience, prompt_get, prompts_list, protocol_version_probe, provenance_divergence_probe, request_association_probe, resource_read, resources_list, schema_divergence_probe, server_card, session_resume_probe, step_up_auth_probe, tool_snapshot_probe, tools_list, transport_compliance_probe, utility_coverage_probe
Aug 11, 2026 07:08:59 AM UTC Completed Healthy 3764.9 ms action_safety_probe, advanced_capabilities_probe, connector_publishability_probe, connector_replay_probe, determinism_probe, initialize, interactive_flow_probe, oauth_authorization_server, oauth_protected_resource, official_registry_probe, openid_configuration, probe_noise_resilience, prompt_get, prompts_list, protocol_version_probe, provenance_divergence_probe, request_association_probe, resource_read, resources_list, schema_divergence_probe, server_card, session_resume_probe, step_up_auth_probe, tool_snapshot_probe, tools_list, transport_compliance_probe, utility_coverage_probe
Incident & change feed
TimestampEventDetails
Aug 15, 2026 03:56:00 AM UTC Latest validation: healthy Score 68.2 with status healthy.
Aug 15, 2026 03:56:00 AM UTC Score changed Score delta -1.6 versus the previous run.
Aug 15, 2026 03:56:00 AM UTC Tool snapshot changed Added 5, removed 0, and changed 0 tool contracts.
Aug 14, 2026 03:54:28 PM UTC Score changed Score delta +0.5 versus the previous run.

Technical details

Raw evidence view
Show raw JSON evidence

Large evidence payload summarized to keep this page fast. Full raw evidence remains available from the JSON report.

{
  "checks": {
    "count": 28,
    "items": {
      "action_safety_probe": {
        "auth_present": true,
        "safeguard_count": 9,
        "status": "warning"
      },
      "advanced_capabilities_probe": {
        "status": "warning"
      },
      "connector_publishability_probe": {
        "status": "warning"
      },
      "connector_replay_probe": {
        "status": "warning"
      },
      "determinism_probe": {
        "latency_ms": 289.41,
        "status": "ok"
      },
      "initialize": {
        "http_status": 200,
        "latency_ms": 343.82,
        "payload_omitted": true,
        "status": "ok"
      },
      "instruction_tool_reference_probe": {
        "status": "warning"
      },
      "interactive_flow_probe": {
        "status": "ok"
      },
      "oauth_authorization_server": {
        "http_status": 200,
        "latency_ms": 456.56,
        "payload_omitted": true,
        "status": "ok"
      },
      "oauth_protected_resource": {
        "http_status": 200,
        "latency_ms": 365.6,
        "payload_omitted": true,
        "status": "ok"
      },
      "official_registry_probe": {
        "status": "missing"
      },
      "openid_configuration": {
        "latency_ms": 332.55,
        "reason": "Client error '404 Not Found' for url 'https://app.epovest.com/.well-known/openid-configuration'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404",
        "status": "error"
      },
      "probe_noise_resilience": {
        "http_status": 200,
        "latency_ms": 398.22,
        "status": "ok"
      },
      "prompt_get": {
        "reason": "not_advertised",
        "status": "missing"
      },
      "prompts_list": {
        "http_status": 401,
        "latency_ms": 135.05,
        "payload_omitted": true,
        "reason": "auth_required",
        "status": "auth_required"
      },
      "protocol_version_probe": {
        "status": "warning"
      },
      "provenance_divergence_probe": {
        "status": "not_assessed"
      },
      "request_association_probe": {
        "reason": "no_request_association_capabilities_advertised",
        "status": "missing"
      },
      "resource_read": {
        "reason": "not_advertised",
        "status": "missing"
      },
      "resources_list": {
        "http_status": 401,
        "latency_ms": 265.76,
        "payload_omitted": true,
        "reason": "auth_required",
        "status": "auth_required"
      },
      "schema_divergence_probe": {
        "reason": "no_server_card_tools",
        "status": "missing"
      },
      "server_card": {
        "latency_ms": 395.13,
        "reason": "Client error '404 Not Found' for url 'https://mcp.epovest.com/.well-known/mcp/server-card.json'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404",
        "status": "error"
      },
      "session_resume_probe": {
        "reason": "no_session_id",
        "status": "warning"
      },
      "step_up_auth_probe": {
        "status": "ok"
      },
      "tool_snapshot_probe": {
        "status": "warning"
      },
      "tools_list": {
        "http_status": 200,
        "latency_ms": 365.6,
        "payload_omitted": true,
        "status": "ok",
        "tool_count": 66,
        "tool_names_preview": [
          "list_trackers",
          "create_tracker",
          "update_tracker",
          "start_tracker",
          "survey_now",
          "pause_tracker",
          "archive_tracker",
          "list_projects",
          "create_project",
          "rename_project",
          "get_canon",
          "update_project_canon",
          "get_link_targets",
          "set_link_targets",
          "archive_project",
          "list_surfaces",
          "create_surface",
          "update_surface",
          "tick_surface_checklist",
          "add_surface_check",
          "update_surface_check",
          "delete_surface_check",
          "restore_surface_check",
          "delete_surface",
          "restore_surface"
        ]
      },
      "transport_compliance_probe": {
        "latency_ms": 93.74,
        "protocol_header_present": false,
        "status": "warning"
      },
      "utility_coverage_probe": {
        "latency_ms": 94.92,
        "status": "ok"
      }
    },
    "omitted_count": 0
  },
  "failures": {
    "count": 2,
    "items": {
      "openid_configuration": {},
      "server_card": {}
    },
    "omitted_count": 0
  },
  "message": "Raw evidence is summarized in HTML to keep server detail pages fast. Use the JSON report or evidence API for the full payload.",
  "remote_url": "https://mcp.epovest.com/mcp",
  "server_card": {
    "name": null,
    "raw_payload_omitted": false,
    "version": null
  },
  "server_identifier": "Epovest/mcp-server",
  "truncated": true
}
Capabilities
Use-case taxonomy
development search communication web
Transport compliance drilldown
Probe status
Warning
Transport
streamable-http
Session header
no
Protocol header
no
Bad protocol response
400
DELETE teardown
n/a
Expired session retry
n/a
Last-Event-ID visible
no

Issues: missing_session_id, missing_protocol_header

Request association
Status
Missing
Advertised capabilities
none
Observed idle methods
none
Violating methods
none
Probe HTTP status
n/a
Issues
none
Connector replay
Status
Warning
Backward compatible
Would break after refresh
Added tools
create_competitor_scan get_competitor_scan list_competitor_scans start_competitor_scan update_competitor_scan
Removed tools
none
Additive output changes
none
Required-argument replay breaks
ToolAdded required argsRemoved required args
No required-argument replay breaks detected.
Output-schema replay breaks
ToolRemoved propertiesAdded properties
No output-schema replay breaks detected.