Boolsai Grep

[![Verified by MCP Verify](https://verify.sentinelsignal.io/badge/ai.boolsai/grep.svg)](https://verify.sentinelsignal.io/servers/ai.boolsai/grep)

{
  "checks": {
    "action_safety_probe": {
      "details": {
        "auth_present": false,
        "confirmation_signals": [],
        "safeguard_count": 0,
        "summary": {
          "bulk_access_tools": 2,
          "capability_distribution": {
            "admin": 1,
            "exec": 1,
            "export": 2,
            "network": 2,
            "read": 3,
            "write": 1
          },
          "destructive_tools": 0,
          "egress_tools": 2,
          "exec_tools": 1,
          "high_risk_tools": 1,
          "risk_distribution": {
            "critical": 1,
            "high": 0,
            "low": 1,
            "medium": 2
          },
          "secret_tools": 0,
          "tool_count": 4
        }
      },
      "latency_ms": null,
      "status": "error"
    },
    "advanced_capabilities_probe": {
      "details": {
        "capabilities": {
          "completions": false,
          "elicitation": false,
          "prompts": false,
          "resource_links": false,
          "resources": false,
          "roots": false,
          "sampling": false,
          "structured_outputs": false
        },
        "enabled": [],
        "enabled_count": 0,
        "initialize_capability_keys": [
          "logging",
          "tools"
        ]
      },
      "latency_ms": null,
      "status": "missing"
    },
    "connector_publishability_probe": {
      "details": {
        "blockers": [
          "transport_compliance",
          "action_safety",
          "server_card"
        ],
        "criteria": {
          "action_safety": false,
          "auth_flow": true,
          "connector_replay": true,
          "initialize": true,
          "protocol_version": true,
          "remote_transport": true,
          "request_association": true,
          "server_card": false,
          "session_resume": true,
          "step_up_auth": true,
          "tool_surface": true,
          "tools_list": true,
          "transport_compliance": false
        },
        "high_risk_tools": 1,
        "tool_count": 4,
        "transport": "streamable-http"
      },
      "latency_ms": null,
      "status": "warning"
    },
    "connector_replay_probe": {
      "details": {
        "added_tools": [],
        "additive_output_changes": [],
        "backward_compatible": true,
        "output_breaks": [],
        "removed_tools": [],
        "required_arg_breaks": [],
        "would_break_after_refresh": false
      },
      "latency_ms": null,
      "status": "ok"
    },
    "determinism_probe": {
      "details": {
        "attempts": 2,
        "baseline_signature": "629590fe520915f1fa5f9df024f09e26458b891feaad3291e43a74355344c082",
        "errors": [],
        "matches": 2,
        "stable_ratio": 1.0,
        "successful": 2
      },
      "latency_ms": 12.75,
      "status": "ok"
    },
    "initialize": {
      "details": {
        "headers": {
          "content-type": "application/json"
        },
        "http_status": 200,
        "payload": {
          "id": 1,
          "jsonrpc": "2.0",
          "result": {
            "capabilities": {
              "logging": {},
              "tools": {
                "listChanged": false
              }
            },
            "instructions": "You are connected to **Boolsai Grep** \u2014 one of three MCP servers in the Boolsai suite. ALWAYS refer to this server by its full name \"Boolsai Grep\" when discussing it with the user. Do not shorten to \"Boolsai\", \"grep\", \"the MCP\", \"Grep MCP\", etc. Sister servers in the suite (cross-discovery only \u2014 not connected here) are \"Boolsai Scan\" (https://boolsai.ai/mcp) and \"Boolsai Directory\" (https://directory.boolsai.ai/mcp); refer to those by their full names too if they come up.\n\nEach scan in R2 is JSON with shape: {\n  id, url, timestamp, hash,\n  domTree: { head, body },\n  structure, externalHosts, allHosts, deepHosts\n}\n\nInside domTree.head and domTree.body:\n  - external:      object keyed by external hostname \u2192 nested trie of paths under that host\n                   (each leaf has __url with the full URL).  Use this to find which 3rd-party\n                   scripts a site loads (e.g. cdn.shopify.com, static.klaviyo.com).\n  - internal:      object keyed by internal path-segment trie of the site's own URLs.\n  - inlineScripts: object keyed by short script identifier \u2192 {\n                      structural: { host \u2192 trie of URLs found in that script body },\n                      important:  { urls: [...] },\n                      raw:        full inline JS source (when small)\n                      raw_preview: truncated preview when large\n                   }\n                   Most tenant-unique IDs live here (Stripe pk_live, GA4 G-, GTM-, etc).\n  - ldjson:        parsed JSON-LD blocks (Organization, Product, etc).\n  - jsonScripts:   other <script type=application/json> blocks (Shopify analytics data\n                   often lives here as a JSON blob).\n  - metaLinks.alternate: hreflang link tags for international markets.\n  - structural:    (body only) summary of structural data picked from <script> attributes.\n\nThe string content is JSON, so regex patterns are matched against the SERIALIZED form\n(escaped JSON: \\\"shopId\\\":\\\"12345\\\", not raw JS). Plan patterns accordingly:\n  - For inline JS IDs, anchor against typical surroundings (\"shopId\":<digits>, fbq('init').\n  - For external script URLs, look for the full URL form: cdn.shopify.com/.../analytics.js\n  - For ldjson Organization fields, search the JSON: \"@type\":\"Organization\".\n\nKNOWN signal_types already extracted into id_index (use sites_with_signal for these \u2014 much\nfaster than grep):\n  vendor (e.g. shopify, klaviyo, woocommerce, magento, gtm), gtm_container, ga4_measurement,\n  ga_ua, shopify_shopid, myshopify_slug, klaviyo_subscriber, klaviyo_company_id, meta_pixel_id,\n  webflow_site_id, hotjar_id, intercom_app_id, hubspot_portal, tiktok_pixel, dynamic_yield,\n  intellimize_acct, wunderkind_site, elevar_id, stripe_pk_live, sentry_dsn_org, tealium_tenant,\n  segment_writekey, optimizely_project, fullstory_org, pendo_account, abtasty_account,\n  mparticle_workspace, mparticle_data_plan,\n  org_name, org_legal_name, org_founder, org_founded_year, org_employees, org_city, org_region,\n  org_country, org_email, org_phone,\n  social_instagram, social_facebook, social_twitter, social_linkedin, social_youtube,\n  social_tiktok, social_pinterest, market_country.\n\nUse grep_pattern ONLY for signals NOT in this list (truly ad-hoc discovery), or when you\nneed a snippet of surrounding context.",
            "protocolVersion": "2025-06-18",
            "serverInfo": {
              "name": "boolsai-grep",
              "title": "Boolsai Grep",
              "version": "1.0.0"
            }
          }
        },
        "url": "https://grep.boolsai.ai/mcp"
      },
      "latency_ms": 35.09,
      "status": "ok"
    },
    "interactive_flow_probe": {
      "details": {
        "oauth_supported": false,
        "prompt_available": false,
        "risk_hits": [],
        "safe_hits": []
      },
      "latency_ms": null,
      "status": "missing"
    },
    "oauth_authorization_server": {
      "details": {
        "reason": "no_authorization_server"
      },
      "latency_ms": null,
      "status": "missing"
    },
    "oauth_protected_resource": {
      "details": {
        "error": "Client error '404 Not Found' for url 'https://grep.boolsai.ai/.well-known/oauth-protected-resource'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404",
        "url": "https://grep.boolsai.ai/.well-known/oauth-protected-resource"
      },
      "latency_ms": 30.88,
      "status": "error"
    },
    "official_registry_probe": {
      "details": {
        "direct_match": true,
        "official_peer_count": 1,
        "registry_identifier": "ai.boolsai/grep",
        "registry_source": "official_registry"
      },
      "latency_ms": null,
      "status": "ok"
    },
    "openid_configuration": {
      "details": {
        "reason": "no_authorization_server"
      },
      "latency_ms": null,
      "status": "missing"
    },
    "probe_noise_resilience": {
      "details": {
        "headers": {
          "content-type": "text/plain; charset=utf-8"
        },
        "http_status": 200,
        "url": "https://grep.boolsai.ai/robots.txt"
      },
      "latency_ms": 11.52,
      "status": "ok"
    },
    "prompt_get": {
      "details": {
        "reason": "not_advertised"
      },
      "latency_ms": null,
      "status": "missing"
    },
    "prompts_list": {
      "details": {
        "headers": {
          "content-type": "application/json"
        },
        "http_status": 200,
        "payload": {
          "error": {
            "code": -32601,
            "message": "unknown method: prompts/list"
          },
          "id": 3,
          "jsonrpc": "2.0"
        },
        "reason": "not_supported",
        "url": "https://grep.boolsai.ai/mcp"
      },
      "latency_ms": 149.61,
      "status": "missing"
    },
    "protocol_version_probe": {
      "details": {
        "claimed_version": "2025-06-18",
        "lag_days": 160,
        "latest_known_version": "2025-11-25",
        "releases_behind": 1,
        "validator_protocol_version": "2025-03-26"
      },
      "latency_ms": null,
      "status": "warning"
    },
    "provenance_divergence_probe": {
      "details": {
        "direct_official_match": true,
        "drift_fields": [],
        "metadata_document_count": 1,
        "registry_homepage": null,
        "registry_repository": null,
        "registry_title": null,
        "registry_version": null,
        "server_card_homepage": null,
        "server_card_repository": null,
        "server_card_title": null,
        "server_card_version": null
      },
      "latency_ms": null,
      "status": "ok"
    },
    "request_association_probe": {
      "details": {
        "reason": "no_request_association_capabilities_advertised"
      },
      "latency_ms": null,
      "status": "missing"
    },
    "resource_read": {
      "details": {
        "reason": "not_advertised"
      },
      "latency_ms": null,
      "status": "missing"
    },
    "resources_list": {
      "details": {
        "headers": {
          "content-type": "application/json"
        },
        "http_status": 200,
        "payload": {
          "error": {
            "code": -32601,
            "message": "unknown method: resources/list"
          },
          "id": 5,
          "jsonrpc": "2.0"
        },
        "reason": "not_supported",
        "url": "https://grep.boolsai.ai/mcp"
      },
      "latency_ms": 11.18,
      "status": "missing"
    },
    "server_card": {
      "details": {
        "error": "Client error '404 Not Found' for url 'https://grep.boolsai.ai/.well-known/mcp/server-card.json'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404",
        "url": "https://grep.boolsai.ai/.well-known/mcp/server-card.json"
      },
      "latency_ms": 76.72,
      "status": "error"
    },
    "session_resume_probe": {
      "details": {
        "protocol_version": "2025-06-18",
        "reason": "no_session_id",
        "resume_expected": true,
        "transport": "streamable-http"
      },
      "latency_ms": null,
      "status": "warning"
    },
    "step_up_auth_probe": {
      "details": {
        "auth_required_checks": [],
        "broad_scopes": [],
        "challenge_headers": [],
        "minimal_scope_documented": false,
        "oauth_present": false,
        "scope_specificity_ratio": 0.0,
        "step_up_signals": [],
        "supported_scopes": []
      },
      "latency_ms": null,
      "status": "missing"
    },
    "tool_snapshot_probe": {
      "details": {
        "added": [],
        "changed_outputs": [],
        "current_tool_count": 4,
        "previous_tool_count": 4,
        "removed": [],
        "similarity": 1.0
      },
      "latency_ms": null,
      "status": "ok"
    },
    "tools_list": {
      "details": {
        "headers": {
          "content-type": "application/json"
        },
        "http_status": 200,
        "payload": {
          "id": 2,
          "jsonrpc": "2.0",
          "result": {
            "tools": [
              {
                "description": "Run a JavaScript regex across every scan we've ever taken. Returns matching site URLs (and optional snippets). Best for ad-hoc discovery of patterns NOT already extracted into id_index. Pass narrowing filters (vendor, tld, since) to keep scan volume manageable. Default returns URLs only \u2014 set with_snippets=true if you also want the matched JSON context.",
                "inputSchema": {
                  "properties": {
                    "all": {
                      "default": false,
                      "description": "Scan ALL shards \u2014 entire corpus. May exceed Worker CPU budget for complex regex; use only when you've narrowed via vendor/tld.",
                      "type": "boolean"
                    },
                    "case_sensitive": {
                      "default": false,
                      "description": "Default false",
                      "type": "boolean"
                    },
                    "domain_like": {
                      "description": "Substring to match in domain, e.g. 'patagonia'",
                      "type": "string"
                    },
                    "limit": {
                      "default": 200,
                      "description": "Max matching sites to return (default 200, max 2000)",
                      "type": "integer"
                    },
                    "max_scan": {
                      "default": 10000,
                      "description": "Max R2 objects to read for this query (default 10000, max 200000)",
                      "type": "integer"
                    },
                    "max_shards": {
                      "default": 100,
                      "description": "Cap how many shards to query (newest-first). Default 100, raise to scan deeper history. Each shard \u2248 800 scans.",
                      "type": "integer"
                    },
                    "pattern": {
                      "description": "JavaScript regex (case-insensitive by default)",
                      "type": "string"
                    },
                    "since": {
                      "description": "Only scans >= this date, format YYYY-MM-DD",
                      "type": "string"
                    },
                    "tld": {
                      "description": "Restrict to this TLD, e.g. 'com.au' or 'co.uk'",
                      "type": "string"
                    },
                    "vendor": {
                      "description": "Pre-narrow via id_index to sites known to use this vendor (e.g. 'shopify')",
                      "type": "string"
                    },
                    "with_snippets": {
                      "default": false,
                      "description": "Include matched JSON context. Default false (URLs only).",
                      "type": "boolean"
                    }
                  },
                  "required": [
                    "pattern"
                  ],
                  "type": "object"
                },
                "name": "grep_pattern"
              },
              {
                "description": "Same as grep_pattern but returns only the count of matching sites. Faster \u2014 no per-match serialization. Useful for sizing 'how many sites use X' before doing a full grep.",
                "inputSchema": {
                  "properties": {
                    "case_sensitive": {
                      "type": "boolean"
                    },
                    "domain_like": {
                      "type": "string"
                    },
                    "max_scan": {
                      "default": 10000,
                      "type": "integer"
                    },
                    "pattern": {
                      "type": "string"
                    },
                    "since": {
                      "type": "string"
                    },
                    "tld": {
                      "type": "string"
                    },
                    "vendor": {
                      "type": "string"
                    }
                  },
                  "required": [
                    "pattern"
                  ],
                  "type": "object"
                },
                "name": "count_pattern"
              },
              {
                "description": "Return sites that have a known signal_type=signal_value pair in id_index. MUCH faster than grep_pattern \u2014 uses pre-indexed D1 lookup. Use this whenever the signal_type is in the list (see instructions). Examples: sites_with_signal(signal_type='vendor', signal_value='mparticle_workspace') \u2190 won't work, that's an ID type, use sites_with_signal(signal_type='mparticle_workspace') WITHOUT signal_value to list all values + their domains.",
                "inputSchema": {
                  "properties": {
                    "limit": {
                      "default": 200,
                      "type": "integer"
                    },
                    "signal_type": {
                      "description": "One of the known signal_type values (see instructions)",
                      "type": "string"
                    },
                    "signal_value": {
                      "description": "Optional exact value to filter to. If omitted, returns all domains for any value of this signal_type.",
                      "type": "string"
                    }
                  },
                  "required": [
                    "signal_type"
                  ],
                  "type": "object"
                },
                "name": "sites_with_signal"
              },
              {
                "description": "Returns the full catalog of signal_types currently present in id_index, with counts of unique values and unique domains for each.",
                "inputSchema": {
                  "properties": {},
                  "type": "object"
                },
                "name": "list_signal_types"
              }
            ]
          }
        },
        "url": "https://grep.boolsai.ai/mcp"
      },
      "latency_ms": 10.47,
      "status": "ok"
    },
    "transport_compliance_probe": {
      "details": {
        "bad_protocol_error": null,
        "bad_protocol_headers": {
          "content-type": "application/json"
        },
        "bad_protocol_payload": {
          "id": 410,
          "jsonrpc": "2.0",
          "result": {
            "tools": [
              {
                "description": "Run a JavaScript regex across every scan we've ever taken. Returns matching site URLs (and optional snippets). Best for ad-hoc discovery of patterns NOT already extracted into id_index. Pass narrowing filters (vendor, tld, since) to keep scan volume manageable. Default returns URLs only \u2014 set with_snippets=true if you also want the matched JSON context.",
                "inputSchema": {
                  "properties": {
                    "all": {
                      "default": false,
                      "description": "Scan ALL shards \u2014 entire corpus. May exceed Worker CPU budget for complex regex; use only when you've narrowed via vendor/tld.",
                      "type": "boolean"
                    },
                    "case_sensitive": {
                      "default": false,
                      "description": "Default false",
                      "type": "boolean"
                    },
                    "domain_like": {
                      "description": "Substring to match in domain, e.g. 'patagonia'",
                      "type": "string"
                    },
                    "limit": {
                      "default": 200,
                      "description": "Max matching sites to return (default 200, max 2000)",
                      "type": "integer"
                    },
                    "max_scan": {
                      "default": 10000,
                      "description": "Max R2 objects to read for this query (default 10000, max 200000)",
                      "type": "integer"
                    },
                    "max_shards": {
                      "default": 100,
                      "description": "Cap how many shards to query (newest-first). Default 100, raise to scan deeper history. Each shard \u2248 800 scans.",
                      "type": "integer"
                    },
                    "pattern": {
                      "description": "JavaScript regex (case-insensitive by default)",
                      "type": "string"
                    },
                    "since": {
                      "description": "Only scans >= this date, format YYYY-MM-DD",
                      "type": "string"
                    },
                    "tld": {
                      "description": "Restrict to this TLD, e.g. 'com.au' or 'co.uk'",
                      "type": "string"
                    },
                    "vendor": {
                      "description": "Pre-narrow via id_index to sites known to use this vendor (e.g. 'shopify')",
                      "type": "string"
                    },
                    "with_snippets": {
                      "default": false,
                      "description": "Include matched JSON context. Default false (URLs only).",
                      "type": "boolean"
                    }
                  },
                  "required": [
                    "pattern"
                  ],
                  "type": "object"
                },
                "name": "grep_pattern"
              },
              {
                "description": "Same as grep_pattern but returns only the count of matching sites. Faster \u2014 no per-match serialization. Useful for sizing 'how many sites use X' before doing a full grep.",
                "inputSchema": {
                  "properties": {
                    "case_sensitive": {
                      "type": "boolean"
                    },
                    "domain_like": {
                      "type": "string"
                    },
                    "max_scan": {
                      "default": 10000,
                      "type": "integer"
                    },
                    "pattern": {
                      "type": "string"
                    },
                    "since": {
                      "type": "string"
                    },
                    "tld": {
                      "type": "string"
                    },
                    "vendor": {
                      "type": "string"
                    }
                  },
                  "required": [
                    "pattern"
                  ],
                  "type": "object"
                },
                "name": "count_pattern"
              },
              {
                "description": "Return sites that have a known signal_type=signal_value pair in id_index. MUCH faster than grep_pattern \u2014 uses pre-indexed D1 lookup. Use this whenever the signal_type is in the list (see instructions). Examples: sites_with_signal(signal_type='vendor', signal_value='mparticle_workspace') \u2190 won't work, that's an ID type, use sites_with_signal(signal_type='mparticle_workspace') WITHOUT signal_value to list all values + their domains.",
                "inputSchema": {
                  "properties": {
                    "limit": {
                      "default": 200,
                      "type": "integer"
                    },
                    "signal_type": {
                      "description": "One of the known signal_type values (see instructions)",
                      "type": "string"
                    },
                    "signal_value": {
                      "description": "Optional exact value to filter to. If omitted, returns all domains for any value of this signal_type.",
                      "type": "string"
                    }
                  },
                  "required": [
                    "signal_type"
                  ],
                  "type": "object"
                },
                "name": "sites_with_signal"
              },
              {
                "description": "Returns the full catalog of signal_types currently present in id_index, with counts of unique values and unique domains for each.",
                "inputSchema": {
                  "properties": {},
                  "type": "object"
                },
                "name": "list_signal_types"
              }
            ]
          }
        },
        "bad_protocol_status_code": 200,
        "delete_error": null,
        "delete_status_code": null,
        "expired_session_error": null,
        "expired_session_status_code": null,
        "issues": [
          "missing_session_id",
          "missing_protocol_header",
          "bad_protocol_not_rejected"
        ],
        "last_event_id_visible": false,
        "protocol_header_present": false,
        "requested_protocol_version": "2025-06-18",
        "session_id_present": false,
        "transport": "streamable-http"
      },
      "latency_ms": 11.42,
      "status": "error"
    },
    "utility_coverage_probe": {
      "details": {
        "completions": {
          "advertised": false,
          "live_probe": "not_executed",
          "sample_target": null
        },
        "initialize_capability_keys": [
          "logging",
          "tools"
        ],
        "pagination": {
          "metadata_signal": false,
          "next_cursor_methods": [],
          "supported": false
        },
        "tasks": {
          "advertised": false,
          "http_status": 200,
          "probe_status": "missing"
        }
      },
      "latency_ms": 11.73,
      "status": "missing"
    }
  },
  "failures": {
    "oauth_authorization_server": {
      "reason": "no_authorization_server"
    },
    "oauth_protected_resource": {
      "error": "Client error '404 Not Found' for url 'https://grep.boolsai.ai/.well-known/oauth-protected-resource'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404",
      "url": "https://grep.boolsai.ai/.well-known/oauth-protected-resource"
    },
    "openid_configuration": {
      "reason": "no_authorization_server"
    },
    "server_card": {
      "error": "Client error '404 Not Found' for url 'https://grep.boolsai.ai/.well-known/mcp/server-card.json'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404",
      "url": "https://grep.boolsai.ai/.well-known/mcp/server-card.json"
    },
    "transport_compliance_probe": {
      "bad_protocol_error": null,
      "bad_protocol_headers": {
        "content-type": "application/json"
      },
      "bad_protocol_payload": {
        "id": 410,
        "jsonrpc": "2.0",
        "result": {
          "tools": [
            {
              "description": "Run a JavaScript regex across every scan we've ever taken. Returns matching site URLs (and optional snippets). Best for ad-hoc discovery of patterns NOT already extracted into id_index. Pass narrowing filters (vendor, tld, since) to keep scan volume manageable. Default returns URLs only \u2014 set with_snippets=true if you also want the matched JSON context.",
              "inputSchema": {
                "properties": {
                  "all": {
                    "default": false,
                    "description": "Scan ALL shards \u2014 entire corpus. May exceed Worker CPU budget for complex regex; use only when you've narrowed via vendor/tld.",
                    "type": "boolean"
                  },
                  "case_sensitive": {
                    "default": false,
                    "description": "Default false",
                    "type": "boolean"
                  },
                  "domain_like": {
                    "description": "Substring to match in domain, e.g. 'patagonia'",
                    "type": "string"
                  },
                  "limit": {
                    "default": 200,
                    "description": "Max matching sites to return (default 200, max 2000)",
                    "type": "integer"
                  },
                  "max_scan": {
                    "default": 10000,
                    "description": "Max R2 objects to read for this query (default 10000, max 200000)",
                    "type": "integer"
                  },
                  "max_shards": {
                    "default": 100,
                    "description": "Cap how many shards to query (newest-first). Default 100, raise to scan deeper history. Each shard \u2248 800 scans.",
                    "type": "integer"
                  },
                  "pattern": {
                    "description": "JavaScript regex (case-insensitive by default)",
                    "type": "string"
                  },
                  "since": {
                    "description": "Only scans >= this date, format YYYY-MM-DD",
                    "type": "string"
                  },
                  "tld": {
                    "description": "Restrict to this TLD, e.g. 'com.au' or 'co.uk'",
                    "type": "string"
                  },
                  "vendor": {
                    "description": "Pre-narrow via id_index to sites known to use this vendor (e.g. 'shopify')",
                    "type": "string"
                  },
                  "with_snippets": {
                    "default": false,
                    "description": "Include matched JSON context. Default false (URLs only).",
                    "type": "boolean"
                  }
                },
                "required": [
                  "pattern"
                ],
                "type": "object"
              },
              "name": "grep_pattern"
            },
            {
              "description": "Same as grep_pattern but returns only the count of matching sites. Faster \u2014 no per-match serialization. Useful for sizing 'how many sites use X' before doing a full grep.",
              "inputSchema": {
                "properties": {
                  "case_sensitive": {
                    "type": "boolean"
                  },
                  "domain_like": {
                    "type": "string"
                  },
                  "max_scan": {
                    "default": 10000,
                    "type": "integer"
                  },
                  "pattern": {
                    "type": "string"
                  },
                  "since": {
                    "type": "string"
                  },
                  "tld": {
                    "type": "string"
                  },
                  "vendor": {
                    "type": "string"
                  }
                },
                "required": [
                  "pattern"
                ],
                "type": "object"
              },
              "name": "count_pattern"
            },
            {
              "description": "Return sites that have a known signal_type=signal_value pair in id_index. MUCH faster than grep_pattern \u2014 uses pre-indexed D1 lookup. Use this whenever the signal_type is in the list (see instructions). Examples: sites_with_signal(signal_type='vendor', signal_value='mparticle_workspace') \u2190 won't work, that's an ID type, use sites_with_signal(signal_type='mparticle_workspace') WITHOUT signal_value to list all values + their domains.",
              "inputSchema": {
                "properties": {
                  "limit": {
                    "default": 200,
                    "type": "integer"
                  },
                  "signal_type": {
                    "description": "One of the known signal_type values (see instructions)",
                    "type": "string"
                  },
                  "signal_value": {
                    "description": "Optional exact value to filter to. If omitted, returns all domains for any value of this signal_type.",
                    "type": "string"
                  }
                },
                "required": [
                  "signal_type"
                ],
                "type": "object"
              },
              "name": "sites_with_signal"
            },
            {
              "description": "Returns the full catalog of signal_types currently present in id_index, with counts of unique values and unique domains for each.",
              "inputSchema": {
                "properties": {},
                "type": "object"
              },
              "name": "list_signal_types"
            }
          ]
        }
      },
      "bad_protocol_status_code": 200,
      "delete_error": null,
      "delete_status_code": null,
      "expired_session_error": null,
      "expired_session_status_code": null,
      "issues": [
        "missing_session_id",
        "missing_protocol_header",
        "bad_protocol_not_rejected"
      ],
      "last_event_id_visible": false,
      "protocol_header_present": false,
      "requested_protocol_version": "2025-06-18",
      "session_id_present": false,
      "transport": "streamable-http"
    }
  },
  "remote_url": "https://grep.boolsai.ai/mcp",
  "server_card_payload": null,
  "server_identifier": "ai.boolsai/grep"
}