← Back to search

Search • Rankings • TrustOps • Docs • Pricing • Claim/Manage

ai.finestructure/fine-structure

Fine Structure

Remote MCP server for agents that create, edit, validate, and publish Fine Structure apps.

JSON report • Policy • Badge metadata • History API • • Global feed

DECISION SUMMARY

Production trust decision

Block For Production

Production readiness

Needs remediation

Score

56.2

Rank suppressed while production readiness shows a blocking verdict.

Confidence

High

Based on evidence completeness, recency, and validation density.

Evidence age

1.2h old

Freshness: fresh. Snapshot trustsnap_cc4d739baa0056dc.

Top risk drivers

Utility Coverage
Transport Compliance
Step Up Auth

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.
Serve /.well-known/oauth-protected-resource and point it at your authorization server metadata.

Next action

revalidate, add safeguards, export policy

exec-capable tools + no confirmation safeguards + high-risk tools need review + score below evaluation threshold

Compare alternatives Export policy Open report JSON Dispute this assessment

Observed Attention

Moderate observed attention

AI discovery detected. This MCP server has recently appeared in AI-assisted discovery or evaluation traffic on Verify.

AI 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.

Risks Compatibility Evidence Fix it Governance History Technical details

Status

Healthy

Score

56.2

Transport

streamable-http

Tools

105

Ownership

Unclaimed

Claim, revalidate, or manage this server

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

105

High-risk tools

Destructive tools

Exec tools

Egress tools

Secret tools

Bulk-access tools

Risk distribution

low:61, medium:41, high:3

Tool capability & risk inventory

Tool	Capabilities	Risk	Findings	Notes	Evidence
`create_app`	write exec	High	command execution freeform input surface	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "write", "exec" ], "input_schema": { "properties": { "description": { "default": "", "description": "Optional short description", "type": "string" }, "name": { "description": "Name for the app (1-100 chars)", "type": "string" }, "prompt": { "description": "Detailed description of the app to build", "type": "string" } }, "required": [ "name", "prompt" ], "type": "object" }, "risk_flags": [ "command_execution", "freeform_input_surface" ] } Dispute this classification
`agency_create_client`	write	Medium	none	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "write" ], "input_schema": { "properties": { "client_email": { "description": "Client email that will be allowed to claim projects", "type": "string" }, "client_full_name": { "default": "", "description": "Optional client display name", "type": "string" }, "note": { "default": "", "description": "Optional internal note for the agency", "type": "string" } }, "required": [ "client_email" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`agency_list_clients`	read	Low	none	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "read" ], "input_schema": { "properties": { "include_handoffs": { "default": true, "description": "Include claim links status without raw tokens", "type": "boolean" } }, "type": "object" }, "risk_flags": [] } Dispute this classification
`agency_create_client_app`	write exec	High	command execution freeform input surface	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "write", "exec" ], "input_schema": { "properties": { "claim_expires_in_days": { "default": 14, "description": "Claim link lifetime, 1-90 days", "type": "integer" }, "client_email": { "description": "Client email allowed to claim ownership", "type": "string" }, "client_full_name": { "default": "", "description": "Optional client display name", "type": "string" }, "description": { "default": "", "description": "Optional short app description", "type": "string" }, "keep_agent_collaborator": { "default": true, "description": "After claim, invite the agent back as an editor collaborator", "type": "boolean" }, "name": { "description": "Name for the app (1-100 chars)", "type": "string" }, "note": { "default": "", "description": "Optional internal client/project note", "type": "string" }, "prompt": { "description": "Detailed description of the app to build", "type": "string" } }, "required": [ "client_email", "name", "prompt" ], "type": "object" }, "risk_flags": [ "command_execution", "freeform_input_surface" ] } Dispute this classification
`agency_create_claim_link`	write	Medium	none	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "write" ], "input_schema": { "properties": { "app_id": { "description": "Existing app ID owned by the agent", "type": "string" }, "claim_expires_in_days": { "default": 14, "description": "Claim link lifetime, 1-90 days", "type": "integer" }, "client_email": { "description": "Client email allowed to claim ownership", "type": "string" }, "client_full_name": { "default": "", "description": "Optional client display name", "type": "string" }, "keep_agent_collaborator": { "default": true, "description": "Invite agent as editor after claim", "type": "boolean" }, "note": { "default": "", "description": "Optional internal note", "type": "string" } }, "required": [ "app_id", "client_email" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`agency_get_claim_status`	read	Low	none	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "read" ], "input_schema": { "properties": { "handoff_id": { "description": "Handoff ID returned by agency_create_claim_link or agency_create_client_app", "type": "string" } }, "required": [ "handoff_id" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`update_app`	write	Medium	freeform input surface	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "write" ], "input_schema": { "properties": { "app_id": { "description": "The app ID to update", "type": "string" }, "prompt": { "description": "What to change in the app", "type": "string" } }, "required": [ "app_id", "prompt" ], "type": "object" }, "risk_flags": [ "freeform_input_surface" ] } Dispute this classification
`publish_app`	read	Low	none	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "read" ], "input_schema": { "properties": { "access_mode": { "default": "infer", "description": "Live access policy. public_open = anyone can view. public_auth = public URL opens but app login is required. private = published snapshot remains owner/collaborator-only. keep = preserve current visibility/auth settings. infer = choose from existing settings and obvious app structure.", "enum": [ "infer", "public_open", "public_auth", "private", "keep" ], "type": "string" }, "app_id": { "description": "The app ID to publish", "type": "string" }, "auth_required": { "description": "Optional explicit override for generated-app login requirement. Prefer access_mode when possible.", "type": "boolean" }, "make_public": { "description": "Optional explicit override for whether published URLs are publicly reachable. Prefer access_mode when possible.", "type": "boolean" } }, "required": [ "app_id" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`get_platform_guide`	read	Low	none	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "read" ], "input_schema": { "properties": { "app_id": { "description": "Optional app ID. If provided, the guide includes a safe app context summary.", "type": "string" }, "sections": { "description": "Optional subset of guide sections to return.", "items": { "enum": [ "ab_testing", "agency", "app_code", "checklists", "data_model", "direct_file_edit", "domains", "file_model", "generation", "media", "overview", "publishing", "saas", "safety", "sdk", "secrets_integrations", "security", "validation" ], "type": "string" }, "type": "array" }, "task_type": { "description": "Optional task hint, for example edit_app, direct_file_edit, seed_data, or publish_app.", "type": "string" } }, "type": "object" }, "risk_flags": [] } Dispute this classification
`get_recommended_workflow`	read	Low	none	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "read" ], "input_schema": { "properties": { "app_id": { "description": "Optional app ID. If provided, the workflow includes a safe app context summary.", "type": "string" }, "goal": { "default": "", "description": "Optional short description of the user's goal.", "type": "string" }, "task_type": { "default": "unknown", "description": "The task type to plan.", "enum": [ "ab_test", "agency_client_app", "create_app", "direct_file_edit", "domain_setup", "edit_app", "fix_runtime_error", "generate_media", "inspect_preview", "publish_app", "saas_setup", "schema_change", "secrets_integration", "security_setup", "seed_data", "unknown", "version_restore" ], "type": "string" } }, "type": "object" }, "risk_flags": [] } Dispute this classification
`get_job_status`	read	Low	none	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "read" ], "input_schema": { "properties": { "job_id": { "description": "The job_id returned by create_app or update_app", "type": "string" } }, "required": [ "job_id" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`get_app_status`	read	Low	none	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "read" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" } }, "required": [ "app_id" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`get_app_links`	read	Low	none	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "read" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" } }, "required": [ "app_id" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`list_app_domains`	read	Low	none	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "read" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" } }, "required": [ "app_id" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`add_custom_domain`	write network	Medium	arbitrary network egress freeform input surface	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "write", "network" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" }, "domain": { "description": "Custom domain to connect, for example example.com or app.example.com", "type": "string" } }, "required": [ "app_id", "domain" ], "type": "object" }, "risk_flags": [ "arbitrary_network_egress", "freeform_input_surface" ] } Dispute this classification
`get_domain_verification`	read network	Medium	arbitrary network egress freeform input surface	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "read", "network" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" }, "domain": { "description": "Optional configured custom domain. If omitted, uses the app's current custom domain.", "type": "string" } }, "required": [ "app_id" ], "type": "object" }, "risk_flags": [ "arbitrary_network_egress", "freeform_input_surface" ] } Dispute this classification
`check_domain_verification`	write network	Medium	arbitrary network egress freeform input surface	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "write", "network" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" }, "domain": { "description": "Optional configured custom domain. If omitted, uses the app's current custom domain.", "type": "string" } }, "required": [ "app_id" ], "type": "object" }, "risk_flags": [ "arbitrary_network_egress", "freeform_input_surface" ] } Dispute this classification
`set_primary_domain`	network	Medium	arbitrary network egress freeform input surface	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "network" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" }, "domain": { "description": "Primary host, for example example.com, www.example.com, or the app subdomain host.", "type": "string" } }, "required": [ "app_id", "domain" ], "type": "object" }, "risk_flags": [ "arbitrary_network_egress", "freeform_input_surface" ] } Dispute this classification
`remove_custom_domain`	network	Medium	arbitrary network egress freeform input surface	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "network" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" }, "domain": { "description": "Optional configured custom domain. If omitted, removes the current custom domain.", "type": "string" } }, "required": [ "app_id" ], "type": "object" }, "risk_flags": [ "arbitrary_network_egress", "freeform_input_surface" ] } Dispute this classification
`get_domain_ssl_status`	read network	Medium	arbitrary network egress freeform input surface	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "read", "network" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" }, "domain": { "description": "Optional configured custom domain. If omitted, uses the app's current custom domain.", "type": "string" } }, "required": [ "app_id" ], "type": "object" }, "risk_flags": [ "arbitrary_network_egress", "freeform_input_surface" ] } Dispute this classification
`configure_domain_redirects`	network	Medium	arbitrary network egress	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "network" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" }, "force_https": { "default": true, "description": "Redirect HTTP custom-domain requests to HTTPS", "type": "boolean" }, "primary_domain": { "description": "Canonical primary domain, for example example.com", "type": "string" }, "redirect_www": { "default": true, "description": "Redirect the www/root counterpart to primary_domain", "type": "boolean" } }, "required": [ "app_id", "primary_domain" ], "type": "object" }, "risk_flags": [ "arbitrary_network_egress" ] } Dispute this classification
`list_apps`	read	Low	none	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "read" ], "input_schema": { "properties": {}, "type": "object" }, "risk_flags": [] } Dispute this classification
`get_app_files`	read	Low	none	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "read" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" } }, "required": [ "app_id" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`read_app_file`	read filesystem	Low	freeform input surface	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "read", "filesystem" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" }, "max_chars": { "default": 200000, "description": "Maximum content characters to return", "type": "integer" }, "path": { "description": "Virtual file path, for example pages/Home.jsx", "type": "string" } }, "required": [ "app_id", "path" ], "type": "object" }, "risk_flags": [ "freeform_input_surface" ] } Dispute this classification
`read_app_files`	read	Low	none	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "read" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" }, "max_chars_per_file": { "default": 100000, "description": "Maximum characters per file", "type": "integer" }, "paths": { "description": "Virtual file paths to read", "items": { "type": "string" }, "type": "array" } }, "required": [ "app_id", "paths" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`write_app_file`	write filesystem	Medium	freeform input surface filesystem mutation	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "write", "filesystem" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" }, "content": { "description": "Complete file contents", "type": "string" }, "file_type": { "description": "Optional file type override", "type": "string" }, "path": { "description": "Virtual file path", "type": "string" } }, "required": [ "app_id", "path", "content" ], "type": "object" }, "risk_flags": [ "freeform_input_surface", "filesystem_mutation" ] } Dispute this classification
`patch_app_file`	write filesystem	Medium	freeform input surface filesystem mutation	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "write", "filesystem" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" }, "new_text": { "description": "Replacement text", "type": "string" }, "old_text": { "description": "Exact existing text to replace", "type": "string" }, "path": { "description": "Virtual file path", "type": "string" }, "replace_all": { "default": false, "description": "Replace all matches instead of the first match", "type": "boolean" } }, "required": [ "app_id", "path", "old_text", "new_text" ], "type": "object" }, "risk_flags": [ "freeform_input_surface", "filesystem_mutation" ] } Dispute this classification
`rename_app_file`	filesystem	Low	freeform input surface	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "filesystem" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" }, "force": { "default": false, "description": "Apply even if validation reports blocking errors", "type": "boolean" }, "new_path": { "description": "New virtual file path", "type": "string" }, "old_path": { "description": "Existing virtual file path to rename", "type": "string" }, "overwrite": { "default": false, "description": "Allow replacing an existing file at new_path", "type": "boolean" } }, "required": [ "app_id", "old_path", "new_path" ], "type": "object" }, "risk_flags": [ "freeform_input_surface" ] } Dispute this classification
`get_app_detail`	read	Low	none	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "read" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" } }, "required": [ "app_id" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`get_entities`	read	Low	none	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "read" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" } }, "required": [ "app_id" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`query_entity`	read	Low	none	Safeguards hinted in metadata.	Schema & evidence { "annotations": {}, "capabilities": [ "read" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" }, "entity": { "description": "Entity name, for example Patient", "type": "string" }, "filters": { "default": {}, "description": "Exact-match field filters", "type": "object" }, "limit": { "default": 100, "description": "Max records to return", "type": "integer" }, "offset": { "default": 0, "description": "Pagination offset", "type": "integer" }, "sort": { "default": "-created_date", "description": "Sort field, prefix with - for descending", "type": "string" } }, "required": [ "app_id", "entity" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`seed_entity`	write	Medium	none	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "write" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" }, "entity": { "description": "Entity name", "type": "string" }, "mode": { "default": "skip_if_not_empty", "description": "append always proposes creation; skip_if_not_empty proposes only when the entity is empty", "enum": [ "append", "skip_if_not_empty" ], "type": "string" }, "reason": { "default": "", "description": "Why these records should be created", "type": "string" }, "records": { "description": "Records to propose for creation after approval", "items": { "type": "object" }, "type": "array" } }, "required": [ "app_id", "entity", "records" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`create_entity_records`	write	Medium	none	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "write" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" }, "entity": { "description": "Entity name", "type": "string" }, "expected_count": { "description": "Optional safety check for the number of proposed records", "type": "integer" }, "reason": { "default": "", "description": "Why these records should be created", "type": "string" }, "records": { "description": "Records to create after approval", "items": { "type": "object" }, "type": "array" } }, "required": [ "app_id", "entity", "records" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`update_entity_record`	write	Medium	none	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "write" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" }, "data": { "description": "Fields to merge into the record", "type": "object" }, "entity": { "description": "Entity name", "type": "string" }, "reason": { "default": "", "description": "Why this record should be updated", "type": "string" }, "record_id": { "description": "Record ID", "type": "string" } }, "required": [ "app_id", "entity", "record_id", "data" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`update_entity_records`	read write	Medium	none	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "read", "write" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" }, "changes": { "description": "Shared fields to merge into every selected record", "type": "object" }, "entity": { "description": "Entity name", "type": "string" }, "expected_count": { "description": "Required match count safety check, when known", "type": "integer" }, "filters": { "description": "One exact-match selector or a list of exact-match selectors", "oneOf": [ { "type": "object" }, { "items": { "type": "object" }, "type": "array" } ] }, "reason": { "default": "", "description": "Why these records should be updated", "type": "string" }, "record_ids": { "description": "Exact record IDs to update", "items": { "type": "string" }, "type": "array" }, "updates": { "description": "Per-record changes; use instead of shared changes", "items": { "properties": { "changes": { "type": "object" }, "record_id": { "type": "string" } }, "required": [ "record_id", "changes" ], "type": "object" }, "type": "array" } }, "required": [ "app_id", "entity" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`delete_entity_records`	read	Low	none	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "read" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" }, "entity": { "description": "Entity name", "type": "string" }, "expected_count": { "description": "Required match count safety check, when known", "type": "integer" }, "filters": { "description": "One exact-match selector or a list of exact-match selectors", "oneOf": [ { "type": "object" }, { "items": { "type": "object" }, "type": "array" } ] }, "reason": { "default": "", "description": "Why these records should be deleted", "type": "string" }, "record_ids": { "description": "Exact record IDs to delete", "items": { "type": "string" }, "type": "array" } }, "required": [ "app_id", "entity" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`get_pages`	read	Low	none	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "read" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" } }, "required": [ "app_id" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`get_errors`	read	Low	none	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "read" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" }, "limit": { "default": 20, "description": "Max errors to return (default 20)", "type": "integer" } }, "required": [ "app_id" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`get_preview_url`	read	Low	none	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "read" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" } }, "required": [ "app_id" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`list_saved_versions`	read	Low	none	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "read" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" } }, "required": [ "app_id" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`restore_saved_version`	read	Low	none	Safeguards hinted in metadata.	Schema & evidence { "annotations": {}, "capabilities": [ "read" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" }, "snapshot_id": { "description": "Saved Version snapshot_id to inspect before restoring in the UI", "type": "string" } }, "required": [ "app_id", "snapshot_id" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`create_change_set`	write	Medium	none	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "write" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" }, "label": { "description": "Optional short label", "type": "string" } }, "required": [ "app_id" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`add_file_change`	write filesystem	Medium	freeform input surface filesystem mutation	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "write", "filesystem" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" }, "change_set_id": { "description": "Change set ID", "type": "string" }, "content": { "default": "", "description": "Complete file contents for upsert", "type": "string" }, "file_type": { "default": "", "description": "Optional file type override", "type": "string" }, "operation": { "default": "upsert", "enum": [ "upsert", "delete" ], "type": "string" }, "path": { "description": "Virtual file path", "type": "string" } }, "required": [ "app_id", "change_set_id", "path" ], "type": "object" }, "risk_flags": [ "freeform_input_surface", "filesystem_mutation" ] } Dispute this classification
`validate_change_set`	undetermined	Low	none	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "undetermined" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" }, "change_set_id": { "description": "Change set ID", "type": "string" }, "include_runtime_errors": { "default": true, "type": "boolean" } }, "required": [ "app_id", "change_set_id" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`apply_change_set`	undetermined	Low	none	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "undetermined" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" }, "change_set_id": { "description": "Change set ID", "type": "string" }, "force": { "default": false, "description": "Apply even if validation has errors", "type": "boolean" } }, "required": [ "app_id", "change_set_id" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`discard_change_set`	undetermined	Low	none	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "undetermined" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" }, "change_set_id": { "description": "Change set ID", "type": "string" } }, "required": [ "app_id", "change_set_id" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`validate_app`	undetermined	Low	none	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "undetermined" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" }, "include_runtime_errors": { "default": true, "type": "boolean" } }, "required": [ "app_id" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`inspect_preview`	read admin	Medium	none	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "read", "admin" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" }, "auth_as": { "default": "", "description": "Optional auth simulation: anonymous", "type": "string" }, "auth_as_role": { "default": "", "description": "Optional app role simulation, e.g. staff/admin/customer", "type": "string" }, "route": { "default": "", "description": "Optional route to inspect", "type": "string" } }, "required": [ "app_id" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`get_app_security_context`	read	Low	none	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "read" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" }, "audit_limit": { "default": 50, "type": "integer" } }, "required": [ "app_id" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`set_route_policy`	write	Medium	none	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "write" ], "input_schema": { "properties": { "allowed_roles": { "description": "Allowed app roles", "items": { "type": "string" }, "type": "array" }, "app_id": { "description": "The app ID", "type": "string" }, "redirect_to": { "default": "/Login", "type": "string" }, "require_auth": { "default": true, "type": "boolean" }, "route": { "description": "Route or wildcard route, e.g. /admin/*", "type": "string" } }, "required": [ "app_id", "route", "require_auth", "allowed_roles" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`set_entity_policy`	read write	Medium	none	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "read", "write" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" }, "entity": { "description": "Entity name, e.g. Booking", "type": "string" }, "read": { "description": "Roles allowed to read", "items": { "type": "string" }, "type": "array" }, "write": { "description": "Roles allowed to write", "items": { "type": "string" }, "type": "array" } }, "required": [ "app_id", "entity", "read", "write" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`list_app_members`	read	Low	none	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "read" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" } }, "required": [ "app_id" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`invite_app_member`	write admin secrets	High	secret material access freeform input surface admin mutation	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "write", "admin", "secrets" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" }, "email": { "description": "Member email", "type": "string" }, "full_name": { "default": "", "type": "string" }, "password": { "description": "Optional initial password. If omitted, one is generated.", "type": "string" }, "role": { "description": "App role, e.g. admin/staff/customer", "type": "string" } }, "required": [ "app_id", "email", "role" ], "type": "object" }, "risk_flags": [ "secret_material_access", "freeform_input_surface", "admin_mutation" ] } Dispute this classification
`update_app_member_role`	write admin	Medium	admin mutation	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "write", "admin" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" }, "role": { "description": "New role", "type": "string" }, "user_id": { "description": "Generated app user id", "type": "string" } }, "required": [ "app_id", "user_id", "role" ], "type": "object" }, "risk_flags": [ "admin_mutation" ] } Dispute this classification
`remove_app_member`	undetermined	Low	none	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "undetermined" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" }, "user_id": { "description": "Generated app user id", "type": "string" } }, "required": [ "app_id", "user_id" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`get_app_security_audit`	read	Low	none	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "read" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" }, "limit": { "default": 100, "type": "integer" } }, "required": [ "app_id" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`compare_saved_versions`	network	Medium	arbitrary network egress	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "network" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" }, "base_snapshot_id": { "description": "Older/base snapshot ID", "type": "string" }, "max_diff_chars": { "default": 12000, "type": "integer" }, "target_snapshot_id": { "description": "Newer/target snapshot ID", "type": "string" } }, "required": [ "app_id", "base_snapshot_id", "target_snapshot_id" ], "type": "object" }, "risk_flags": [ "arbitrary_network_egress" ] } Dispute this classification
`compare_current_to_version`	undetermined	Low	none	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "undetermined" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" }, "max_diff_chars": { "default": 12000, "type": "integer" }, "snapshot_id": { "description": "Saved Version snapshot ID", "type": "string" } }, "required": [ "app_id", "snapshot_id" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`restore_file_from_version`	filesystem	Low	freeform input surface	Safeguards hinted in metadata.	Schema & evidence { "annotations": {}, "capabilities": [ "filesystem" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" }, "confirm": { "default": false, "type": "boolean" }, "path": { "description": "Virtual file path to restore", "type": "string" }, "snapshot_id": { "description": "Saved Version snapshot ID", "type": "string" } }, "required": [ "app_id", "snapshot_id", "path", "confirm" ], "type": "object" }, "risk_flags": [ "freeform_input_surface" ] } Dispute this classification
`create_entity_schema`	write	Medium	none	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "write" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" }, "entity": { "description": "Entity name", "type": "string" }, "indexes": { "default": [], "items": { "type": "object" }, "type": "array" }, "metadata": { "default": {}, "type": "object" }, "overwrite": { "default": false, "type": "boolean" }, "relationships": { "default": [], "items": { "type": "object" }, "type": "array" }, "schema": { "description": "JSON schema object", "type": "object" } }, "required": [ "app_id", "entity", "schema" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`update_entity_schema`	write	Medium	none	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "write" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" }, "entity": { "description": "Entity name", "type": "string" }, "indexes": { "default": [], "items": { "type": "object" }, "type": "array" }, "merge": { "default": true, "type": "boolean" }, "metadata": { "default": {}, "type": "object" }, "relationships": { "default": [], "items": { "type": "object" }, "type": "array" }, "schema": { "description": "Schema fields to set or merge", "type": "object" } }, "required": [ "app_id", "entity", "schema" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`validate_entity_relationships`	undetermined	Low	none	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "undetermined" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" } }, "required": [ "app_id" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`update_entity_metadata`	write	Medium	none	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "write" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" }, "entity": { "description": "Entity name", "type": "string" }, "indexes": { "default": [], "items": { "type": "object" }, "type": "array" }, "metadata": { "default": {}, "type": "object" }, "relationships": { "default": [], "items": { "type": "object" }, "type": "array" } }, "required": [ "app_id", "entity" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`list_secret_keys`	read	Low	none	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "read" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" } }, "required": [ "app_id" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`set_secret`	write	Medium	none	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "write" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" }, "key": { "description": "Secret key name", "type": "string" }, "value": { "description": "Secret value to encrypt and store", "type": "string" } }, "required": [ "app_id", "key", "value" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`delete_secret`	undetermined	Low	none	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "undetermined" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" }, "key": { "description": "Secret key name", "type": "string" } }, "required": [ "app_id", "key" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`list_integrations`	read	Low	none	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "read" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" } }, "required": [ "app_id" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`configure_integration`	undetermined	Low	none	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "undetermined" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" }, "config": { "description": "Safe metadata only, such as workspace/team/name/email", "type": "object" }, "is_active": { "default": true, "description": "Set false to disconnect this integration metadata", "type": "boolean" }, "provider": { "description": "Integration provider ID", "type": "string" } }, "required": [ "app_id", "provider", "config" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`list_ab_tests`	read	Low	none	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "read" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" } }, "required": [ "app_id" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`create_ab_test`	write export	Medium	bulk data access	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "write", "export" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" }, "goal_event_filter": { "description": "Optional goal filter, for example {'entity_name': 'Lead'}", "type": "object" }, "goal_event_type": { "description": "Optional conversion goal type: entity_create, any, form_submit", "type": "string" }, "is_active": { "default": true, "description": "Whether to activate the test immediately", "type": "boolean" }, "name": { "description": "Experiment name", "type": "string" }, "page_name": { "description": "Base route page that triggers the experiment", "type": "string" }, "variants": { "description": "At least two variants. Traffic must total 100.", "items": { "properties": { "page_name": { "description": "Existing app page name or path", "type": "string" }, "traffic_percent": { "description": "Traffic percentage for this variant", "type": "integer" } }, "required": [ "page_name", "traffic_percent" ], "type": "object" }, "type": "array" } }, "required": [ "app_id", "name", "page_name", "variants" ], "type": "object" }, "risk_flags": [ "bulk_data_access" ] } Dispute this classification
`update_ab_test`	write export	Medium	bulk data access	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "write", "export" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" }, "goal_event_filter": { "description": "Optional conversion goal filter", "type": "object" }, "goal_event_type": { "description": "Optional conversion goal type", "type": "string" }, "is_active": { "description": "Optional active state", "type": "boolean" }, "name": { "description": "Optional new name", "type": "string" }, "page_name": { "description": "Optional new base route page", "type": "string" }, "test_id": { "description": "A/B test ID", "type": "string" }, "variants": { "description": "Optional replacement variants. Traffic must total 100.", "items": { "type": "object" }, "type": "array" } }, "required": [ "app_id", "test_id" ], "type": "object" }, "risk_flags": [ "bulk_data_access" ] } Dispute this classification
`delete_ab_test`	undetermined	Low	none	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "undetermined" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" }, "test_id": { "description": "A/B test ID", "type": "string" } }, "required": [ "app_id", "test_id" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`get_ab_test_stats`	read	Low	none	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "read" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" }, "test_id": { "description": "A/B test ID", "type": "string" } }, "required": [ "app_id", "test_id" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`email_marketing_status`	read	Low	none	Safeguards hinted in metadata.	Schema & evidence { "annotations": {}, "capabilities": [ "read" ], "input_schema": { "properties": { "include_logs": { "default": false, "description": "Include recent delivery logs", "type": "boolean" } }, "type": "object" }, "risk_flags": [] } Dispute this classification
`email_marketing_configure_sender`	undetermined	Low	none	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "undetermined" ], "input_schema": { "properties": { "default_timezone": { "description": "Default timezone for scheduling", "type": "string" }, "is_enabled": { "description": "Enable or disable the module at settings level", "type": "boolean" }, "organization_name": { "description": "Organization name used in unsubscribe footer", "type": "string" }, "postal_address": { "description": "Optional postal/contact address for compliance", "type": "string" }, "reply_to": { "description": "Reply-To email address", "type": "string" }, "sender_email": { "description": "Sender email address used by the email provider", "type": "string" }, "sender_name": { "description": "Display sender name", "type": "string" } }, "type": "object" }, "risk_flags": [] } Dispute this classification
`email_marketing_update_template`	write	Medium	freeform input surface	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "write" ], "input_schema": { "properties": { "body_html": { "description": "HTML body with {{variables}}", "type": "string" }, "enabled": { "description": "Whether this automatic template is active", "type": "boolean" }, "subject": { "description": "Email subject with {{variables}}", "type": "string" }, "template_id": { "description": "Template/event id, e.g. user_joined", "type": "string" } }, "required": [ "template_id" ], "type": "object" }, "risk_flags": [ "freeform_input_surface" ] } Dispute this classification
`email_marketing_create_broadcast`	read write	Medium	none	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "read", "write" ], "input_schema": { "properties": { "body_html": { "description": "HTML body. Unsubscribe is appended automatically.", "type": "string" }, "filters": { "description": "Recipient filters: plans, roles, active_status, email_verified, min_apps, max_apps, has_published_app, search", "type": "object" }, "name": { "description": "Internal campaign name", "type": "string" }, "scheduled_at": { "description": "Optional ISO datetime. If no timezone is included, timezone is used.", "type": "string" }, "send_now": { "default": false, "description": "Send immediately after creating the campaign", "type": "boolean" }, "subject": { "description": "Email subject", "type": "string" }, "timezone": { "default": "UTC", "description": "Timezone for naive scheduled_at", "type": "string" } }, "required": [ "subject", "body_html" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`email_marketing_create_sequence`	write	Medium	none	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "write" ], "input_schema": { "properties": { "filters": { "description": "Recipient filters", "type": "object" }, "name": { "description": "Sequence name", "type": "string" }, "schedule_mode": { "description": "fixed_dates uses each step.scheduled_at; day_offsets uses start_at + step day offsets", "enum": [ "fixed_dates", "day_offsets" ], "type": "string" }, "start_at": { "description": "ISO datetime for day_offsets mode", "type": "string" }, "steps": { "description": "Steps with subject, body_html, and either scheduled_at (fixed_dates) or day_offset/gap_days (day_offsets).", "items": { "type": "object" }, "type": "array" }, "timezone": { "default": "UTC", "type": "string" } }, "required": [ "name", "schedule_mode", "steps" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`email_marketing_create_variable_trigger`	write	Medium	none	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "write" ], "input_schema": { "properties": { "body_html": { "description": "HTML body. Unsubscribe is appended automatically.", "type": "string" }, "enabled": { "default": true, "type": "boolean" }, "filters": { "description": "Optional recipient filters", "type": "object" }, "from_value": { "description": "Previous value or empty wildcard", "type": "string" }, "name": { "description": "Trigger name", "type": "string" }, "subject": { "description": "Email subject", "type": "string" }, "to_value": { "description": "New value or empty wildcard", "type": "string" }, "variable_name": { "description": "Variable name, e.g. plan", "type": "string" } }, "required": [ "variable_name", "subject", "body_html" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`email_marketing_trigger_variable`	undetermined	Low	none	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "undetermined" ], "input_schema": { "properties": { "context": { "description": "Extra template variables", "type": "object" }, "from_value": { "description": "Previous value", "type": "string" }, "to_value": { "description": "New value", "type": "string" }, "user_id": { "description": "Platform user id", "type": "string" }, "variable_name": { "description": "Variable name", "type": "string" } }, "required": [ "user_id", "variable_name" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`email_marketing_app_status`	read	Low	none	Safeguards hinted in metadata.	Schema & evidence { "annotations": {}, "capabilities": [ "read" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" }, "include_logs": { "default": false, "type": "boolean" } }, "required": [ "app_id" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`email_marketing_app_configure`	undetermined	Low	none	Safeguards hinted in metadata.	Schema & evidence { "annotations": {}, "capabilities": [ "undetermined" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" }, "default_contact_entity": { "description": "Entity to sync as contacts, e.g. Customer or Lead", "type": "string" }, "default_email_field": { "description": "Field containing contact email", "type": "string" }, "default_name_field": { "description": "Field containing contact name", "type": "string" }, "is_enabled": { "type": "boolean" }, "reply_to": { "type": "string" }, "sender_email": { "type": "string" }, "sender_name": { "type": "string" } }, "required": [ "app_id" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`email_marketing_app_sync_contacts`	undetermined	Low	none	Safeguards hinted in metadata.	Schema & evidence { "annotations": {}, "capabilities": [ "undetermined" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" }, "email_field": { "default": "email", "type": "string" }, "entity_name": { "description": "Entity name, e.g. Customer or Lead", "type": "string" }, "limit": { "default": 1000, "type": "integer" }, "name_field": { "type": "string" } }, "required": [ "app_id", "entity_name" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`email_marketing_app_create_broadcast`	read write	Medium	none	Safeguards hinted in metadata.	Schema & evidence { "annotations": {}, "capabilities": [ "read", "write" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" }, "body_html": { "type": "string" }, "filters": { "description": "App contact filters such as source_entity, search, tags, field_equals", "type": "object" }, "name": { "type": "string" }, "scheduled_at": { "type": "string" }, "send_now": { "default": false, "type": "boolean" }, "subject": { "type": "string" }, "timezone": { "default": "UTC", "type": "string" } }, "required": [ "app_id", "subject", "body_html" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`email_marketing_app_create_event_trigger`	write	Medium	none	Safeguards hinted in metadata.	Schema & evidence { "annotations": {}, "capabilities": [ "write" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" }, "body_html": { "type": "string" }, "enabled": { "default": true, "type": "boolean" }, "entity_name": { "description": "Optional entity filter", "type": "string" }, "event_name": { "description": "Event name, e.g. entity_created, Customer.created, order_paid", "type": "string" }, "filters": { "description": "Optional app contact filters", "type": "object" }, "name": { "type": "string" }, "subject": { "type": "string" } }, "required": [ "app_id", "event_name", "subject", "body_html" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`email_marketing_app_record_event`	write	Medium	none	Safeguards hinted in metadata.	Schema & evidence { "annotations": {}, "capabilities": [ "write" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" }, "contact_id": { "type": "string" }, "email": { "description": "Contact email if no contact_id is known", "type": "string" }, "entity_name": { "type": "string" }, "event_name": { "type": "string" }, "properties": { "description": "Extra event properties", "type": "object" }, "record": { "description": "Entity record fields for template variables and contact extraction", "type": "object" }, "record_id": { "type": "string" } }, "required": [ "app_id", "event_name" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`email_marketing_app_create_workflow`	write	Medium	none	Safeguards hinted in metadata.	Schema & evidence { "annotations": {}, "capabilities": [ "write" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" }, "definition": { "description": "Optional full workflow definition; steps can also be supplied here.", "type": "object" }, "enabled": { "default": true, "type": "boolean" }, "name": { "type": "string" }, "steps": { "description": "Ordered workflow steps. Supported type values: email, wait, condition, split, goal.", "items": { "type": "object" }, "type": "array" }, "trigger_entity_name": { "description": "Optional entity filter", "type": "string" }, "trigger_event_name": { "description": "Event that enrolls a contact, e.g. Customer.created", "type": "string" } }, "required": [ "app_id", "trigger_event_name" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`email_marketing_app_create_sequence`	write	Medium	none	Safeguards hinted in metadata.	Schema & evidence { "annotations": {}, "capabilities": [ "write" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" }, "filters": { "description": "App contact filters", "type": "object" }, "name": { "type": "string" }, "schedule_mode": { "default": "day_offsets", "enum": [ "fixed_dates", "day_offsets" ], "type": "string" }, "start_at": { "description": "Sequence start date/time for day_offsets mode", "type": "string" }, "steps": { "description": "Emails in order. Each step supports subject, body_html, scheduled_at, day_offset, or gap_days.", "items": { "type": "object" }, "type": "array" }, "timezone": { "default": "UTC", "type": "string" } }, "required": [ "app_id", "steps" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`email_marketing_app_report`	read	Low	none	Safeguards hinted in metadata.	Schema & evidence { "annotations": {}, "capabilities": [ "read" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" }, "include_events": { "default": true, "type": "boolean" }, "limit": { "default": 50, "type": "integer" }, "segment_limit": { "default": 25, "type": "integer" } }, "required": [ "app_id" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`email_marketing_app_create_segment`	write	Medium	none	Safeguards hinted in metadata.	Schema & evidence { "annotations": {}, "capabilities": [ "write" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" }, "filters": { "description": "Segment filters. Supports rules with field/operator/value plus opened/clicked/sent behavior fields.", "type": "object" }, "name": { "type": "string" }, "sample_limit": { "default": 10, "type": "integer" } }, "required": [ "app_id", "name", "filters" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`email_marketing_app_contact_profile`	read	Low	none	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "read" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" }, "contact": { "description": "Contact id or email address", "type": "string" } }, "required": [ "app_id", "contact" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`email_marketing_app_deliverability`	read	Low	none	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "read" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" } }, "required": [ "app_id" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`email_marketing_app_process_queue`	undetermined	Low	none	Safeguards hinted in metadata.	Schema & evidence { "annotations": {}, "capabilities": [ "undetermined" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" }, "max_jobs": { "default": 50, "type": "integer" } }, "required": [ "app_id" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`email_marketing_app_queue_status`	read	Low	none	Safeguards hinted in metadata.	Schema & evidence { "annotations": {}, "capabilities": [ "read" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" }, "limit": { "default": 50, "type": "integer" }, "status": { "description": "Optional queue status filter", "type": "string" } }, "required": [ "app_id" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`email_marketing_app_suppress_contact`	undetermined	Low	none	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "undetermined" ], "input_schema": { "properties": { "app_id": { "description": "The app ID", "type": "string" }, "email": { "type": "string" }, "metadata": { "type": "object" }, "reason": { "default": "manual", "type": "string" }, "source": { "default": "mcp", "type": "string" } }, "required": [ "app_id", "email" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`list_media_capabilities`	read	Low	none	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "read" ], "input_schema": { "properties": { "surfaces": { "description": "Limit the answer to these surfaces. Default: all three.", "items": { "enum": [ "image", "video", "slideshow" ], "type": "string" }, "type": "array" } }, "type": "object" }, "risk_flags": [] } Dispute this classification
`generate_image`	network	Medium	arbitrary network egress freeform input surface	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "network" ], "input_schema": { "properties": { "language": { "description": "Language of any text in the image. ISO code such as 'en' or 'he'. Defaults to 'en'.", "type": "string" }, "notify_by_email": { "default": false, "description": "Email the account owner the finished image. Default false so batch runs do not spam.", "type": "boolean" }, "prompt": { "description": "What to draw. Up to 4500 chars.", "type": "string" }, "reference_image_data_url": { "description": "Reference image inline as a data:image/... URL. Prefer reference_image_url for large files.", "type": "string" }, "reference_image_data_urls": { "description": "Up to 6 extra reference images as data:image/... URLs.", "items": { "type": "string" }, "type": "array" }, "reference_image_url": { "description": "Public https URL of a reference image, or one of this account's own finestructure.ai uploads.", "type": "string" } }, "required": [ "prompt" ], "type": "object" }, "risk_flags": [ "arbitrary_network_egress", "freeform_input_surface" ] } Dispute this classification
`estimate_video_cost`	undetermined	Low	none	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "undetermined" ], "input_schema": { "properties": { "duration": { "description": "Seconds. Snapped to the model's allowed values.", "type": "integer" }, "model": { "description": "Model id from list_media_capabilities. Default 'seedance-2'.", "type": "string" }, "resolution": { "description": "480p, 720p, or 1080p (model dependent).", "type": "string" } }, "type": "object" }, "risk_flags": [] } Dispute this classification
`generate_video`	undetermined	Low	freeform input surface	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "undetermined" ], "input_schema": { "properties": { "aspect_ratio": { "description": "auto, 16:9, 9:16, 1:1, 4:3, 3:4, or 21:9. Default auto.", "type": "string" }, "duration": { "description": "Seconds. Snapped to the model's allowed values.", "type": "integer" }, "image_urls": { "description": "Up to 9 public https reference images (Seedance models only).", "items": { "type": "string" }, "type": "array" }, "max_charge_usd": { "description": "Refuse the render if it would charge more than this. Strongly recommended for autonomous agents.", "type": "number" }, "model": { "description": "Model id from list_media_capabilities. Default 'seedance-2'.", "type": "string" }, "prompt": { "description": "The shot to render. Up to 4000 chars.", "type": "string" }, "resolution": { "description": "480p, 720p, or 1080p (model dependent). Default 480p.", "type": "string" } }, "required": [ "prompt" ], "type": "object" }, "risk_flags": [ "freeform_input_surface" ] } Dispute this classification
`get_video_status`	read	Low	none	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "read" ], "input_schema": { "properties": { "job_id": { "description": "Job id returned by generate_video.", "type": "string" } }, "required": [ "job_id" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`list_video_jobs`	read	Low	none	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "read" ], "input_schema": { "properties": { "limit": { "description": "How many jobs to return, 1-100. Default 20.", "type": "integer" } }, "type": "object" }, "risk_flags": [] } Dispute this classification
`generate_slideshow`	write network	Medium	arbitrary network egress freeform input surface	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "write", "network" ], "input_schema": { "properties": { "accent_color": { "description": "Hex accent for the chip text style.", "type": "string" }, "authentic_mode": { "description": "Lowercase, unpolished 'real person' voice.", "type": "boolean" }, "collection": { "description": "Saved photo collection id to pull slide photos from.", "type": "string" }, "content_style": { "description": "Copy archetype, e.g. x_ways, storytelling, countdown_ranking.", "type": "string" }, "cta_platforms": { "description": "What the CTA actually offers.", "items": { "enum": [ "ios", "android", "web" ], "type": "string" }, "type": "array" }, "cta_url": { "description": "Link promoted on the final slide. Omit for pure-value content.", "type": "string" }, "enhanced": { "description": "Use the higher-quality (more expensive) image model.", "type": "boolean" }, "goal": { "description": "What the slideshow should achieve or teach.", "type": "string" }, "language": { "description": "ISO code such as 'en' or 'he'. Defaults to 'en'.", "type": "string" }, "narrative_device": { "description": "Framing device, e.g. metaphor or famous_quote.", "type": "string" }, "render_images": { "default": false, "description": "Start rendering images immediately after the script. Default false (review first).", "type": "boolean" }, "sales_bridge": { "description": "Add pre-sale bridge slides before the offer.", "type": "boolean" }, "series_part": { "description": "Part number for a recurring series.", "type": "integer" }, "slide_count": { "description": "Fixed number of slides. Omit for the style's natural range.", "type": "integer" }, "template": { "description": "Built-in template id whose voice spec dominates the output.", "type": "string" }, "text_align": { "description": "left, right, or center.", "type": "string" }, "visual_style": { "description": "Visual look, e.g. bold_gradient, tiktok_native_photo.", "type": "string" }, "voice_spec": { "description": "A reference voice spec to reproduce exactly.", "type": "string" }, "with_graphics": { "description": "Rich visuals vs clean text-only slides. Default true.", "type": "boolean" }, "x_ways_substyle": { "description": "How numbered ways are written (x_ways content style only).", "type": "string" } }, "required": [ "goal" ], "type": "object" }, "risk_flags": [ "arbitrary_network_egress", "freeform_input_surface" ] } Dispute this classification
`render_slideshow_images`	undetermined	Low	none	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "undetermined" ], "input_schema": { "properties": { "history_id": { "description": "history_id returned by generate_slideshow.", "type": "integer" } }, "required": [ "history_id" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`get_slideshow`	read	Low	none	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "read" ], "input_schema": { "properties": { "history_id": { "description": "history_id returned by generate_slideshow.", "type": "integer" } }, "required": [ "history_id" ], "type": "object" }, "risk_flags": [] } Dispute this classification
`list_slideshows`	read	Low	none	No explicit safeguard hints detected.	Schema & evidence { "annotations": {}, "capabilities": [ "read" ], "input_schema": { "properties": { "limit": { "description": "How many to return, 1-60. Default 20.", "type": "integer" } }, "type": "object" }, "risk_flags": [] } Dispute this classification

Write-action governance

Governance status

Error

Safe to publish

Auth boundary

public_or_unclear

Blast radius

High

High-risk tools

Confirmation signals

get_app_links, seed_entity, create_entity_records, update_entity_record, update_entity_records, delete_entity_records, get_preview_url, restore_saved_version, inspect_preview, render_slideshow_images

Safeguard count

Status detail: 3 high-risk tool(s), 2 exec-capable tool(s) are exposed without a clear auth boundary; 16 safeguard(s) and 10 confirmation signal(s) detected.

Tool	Risk	Flags	Safeguards
`create_app`	High	command execution freeform input surface	no
`agency_create_client_app`	High	command execution freeform input surface	no
`invite_app_member`	High	secret material access freeform input surface admin mutation	no

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

Disabled-by-default candidates

none

New actions

Action	Risk	Flags
No newly added actions.

Changed actions

Action	Change types	Risk
No materially changed actions.

Critical alerts

High/critical-severity alerts

Production verdicts degrade quickly when high or critical-severity alerts are active.

Compatibility

Client compatibility 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

OpenAI connectors expect OAuth for remote server auth.; Dynamic client registration materially improves connector setup.; Transport compliance failed or did not complete successfully.; OAuth interoperability should be strong.; 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.

Confidence: high (77.5)

Evidence provenance

Winner: live_validation

Supporting sources: live_validation, history, server_card

Disagreements: none

initialize • OK
tools_list • OK
transport_compliance_probe • Error
step_up_auth_probe • Missing
connector_replay_probe • OK — Frozen tool snapshots must survive refresh.
request_association_probe • Missing — Roots, sampling, and elicitation should stay request-scoped.

Client compatibility: Claude

Not client-compatible

Transport behavior should match Claude-compatible HTTP expectations.; 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.; OAuth is not configured, so this client cannot authenticate without additional setup.; 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.

Confidence: high (77.5)

Evidence provenance

Winner: live_validation

Supporting sources: live_validation, history, server_card

Disagreements: none

initialize • OK
tools_list • OK
transport_compliance_probe • Error

Write-action publishing

Publishing blocked

action_safety_probe reported an unconfirmed high-risk, destructive, or exec-capable tool. Risky write actions are present without a clear auth boundary and confirmation signal.

Confidence: high (77.5)

Evidence provenance

Winner: live_validation

Supporting sources: live_validation, history

Disagreements: none

action_safety_probe • Error

Snapshot churn risk

Low

No material tool-surface churn detected in the latest comparison.

Confidence: high (77.5)

Evidence provenance

Winner: history

Supporting sources: history, live_validation

Disagreements: none

tool_snapshot_probe • OK
connector_replay_probe • OK

Client compatibility gate details

ChatGPT custom connector

Not client-compatible

Remediation checklist

Add OAuth-based authentication for remote connector auth.
Support dynamic client registration (DCR) to simplify connector setup.
Resolve the transport compliance failure -- see the transport compliance probe evidence for what specifically broke.
Improve OAuth interoperability -- see the OAuth Interop score breakdown.
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.

Claude remote MCP

Not client-compatible

Remediation checklist

Resolve the transport compliance failure -- see the transport compliance probe evidence for what specifically broke.
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.
Configure OAuth for authenticated remote MCP access.
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.

Write-safe publishing

Blocked

Risky write or non-read tools are exposed without a clear auth boundary.; Exec-capable tools are exposed.; Production readiness shows a blocking verdict.

Remediation checklist

Add a clearer auth boundary around risky write actions.
Constrain or sandbox exec-capable tools before publishing broadly.
Resolve the blocking production-readiness verdict before treating this as write-safe.

Verdict traces

Production verdict

Needs remediation

Current validation evidence shows operational or discovery gaps that should be fixed first.

Confidence: high (77.5)

Winning source: live_validation

Triggering alerts

No active alert triggers.

Client verdict trace table

Verdict	Status	Checks	Winning source	Conflicts
`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`	Low	tool_snapshot_probe, connector_replay_probe	history	none

Publishability policy profiles

ChatGPT custom connector compatibility

Compatible with review

Search Fetch Only: No
Write Actions Present: Yes
Oauth Configured: No
Admin Refresh Required: No
Safe For Company Knowledge: No
Safe For Messages Api Remote Mcp: No

Claude remote MCP compatibility

Connector-compatible

Search Fetch Only: No
Write Actions Present: Yes
Oauth Configured: No
Admin Refresh Required: No
Safe For Company Knowledge: No
Safe For Messages Api Remote Mcp: No

Compatibility fixtures

ChatGPT custom connector fixture

Degraded

remote_http_endpoint: Passes
oauth_discovery: Degraded
frozen_tool_snapshot_refresh: Passes
request_association: Not Assessed

Anthropic remote MCP fixture

Degraded

Transport behavior should match Claude-compatible HTTP expectations.

remote_transport: Passes
tool_discovery: Passes
auth_connect: Passes
safe_write_review: Degraded

Recommended for

Claude Desktop

Claude Desktop is marked compatible with score 83.

Generic Streamable HTTP

Generic Streamable HTTP is marked compatible with score 100.

Evidence

Current trust snapshot

Snapshot ID

trustsnap_cc4d739baa0056dc

Use this ID to compare server page, report, policy, MCP, homepage, ranking, and shortlist surfaces.

Snapshot generated

Aug 12, 2026 02:38:57 PM UTC

All page, report, policy, and MCP surfaces use this same server-detail snapshot shape.

Last validated

Aug 12, 2026 01:29:55 PM UTC

Age: 1.15h • evidence age tier: Verified in last 24h • display score: 56.25

Canonical machine links

Compare index

/compare.json

Compare API

/v1/compare?server=ai.finestructure%2Ffine-structure

Trust summary

/v1/servers/ai.finestructure/fine-structure/trust-summary

Report JSON

/v1/servers/ai.finestructure/fine-structure/report

Policy export

/v1/servers/ai.finestructure/fine-structure/policy

Badge metadata

/v1/servers/ai.finestructure/fine-structure/badge

Ledger evidence

/v1/servers/ai.finestructure/fine-structure/ledger

Human compare URL

/compare?server=ai.finestructure%2Ffine-structure

Evidence confidence

Confidence score

77.5

Based on 2 recent validations, 11 captured checks, and validation age of 1.2 hours.

Live checks captured

More direct checks increase trust in the current verdict.

Validation age

1.1h

Lower age means fresher evidence.

Latest validation evidence

Latest summary

Healthy

Validation profile

remote_mcp

Started

Aug 12, 2026 01:29:55 PM UTC

Latency

545.5 ms

Failures

oauth_authorization_server no authorization server
oauth_protected_resource Non-MCP content type: text/html
openid_configuration no authorization server
server_card Client error '404 Not Found' for url 'https://finestructure.ai/.well-known/mcp/server-card.json' For more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/404
transport_compliance_probe Issues: missing session id, missing protocol header, bad protocol not rejected (bad protocol=200).

Checks

Check	Status	Latency	Evidence
`action_safety_probe`	Error	n/a	3 high-risk, 2 exec-capable, 10 egress-capable, 2 bulk-access, non-read capabilities: write, exec, export tool(s); no clear auth boundary; safeguards=16; confirmation=get app links, seed entity, create entity records, update entity record, +6 more.
`advanced_capabilities_probe`	Missing	n/a	No advanced MCP capability signals detected.
`connector_publishability_probe`	Warning	n/a	Publishability blockers: step up auth, transport compliance, request association, action safety, +1 more.
`connector_replay_probe`	OK	n/a	Backward compatible with no breaking tool-surface changes.
`determinism_probe`	OK	25.8 ms	Check completed
`initialize`	OK	63.4 ms	Protocol 2024-11-05
`interactive_flow_probe`	OK	n/a	Check completed
`oauth_authorization_server`	Missing	n/a	no authorization server
`oauth_protected_resource`	Error	60.4 ms	Non-MCP content type: text/html
`official_registry_probe`	OK	n/a	Check completed
`openid_configuration`	Missing	n/a	no authorization server
`probe_noise_resilience`	OK	90.2 ms	Fetched https://finestructure.ai/robots.txt
`prompt_get`	Missing	n/a	not advertised
`prompts_list`	Missing	20.9 ms	not supported
`protocol_version_probe`	Warning	n/a	Claims 2024-11-05; 3 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`	Missing	21.8 ms	not supported
`schema_divergence_probe`	Missing	n/a	no server card tools
`server_card`	Error	41.5 ms	Client error '404 Not Found' for url 'https://finestructure.ai/.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`	Missing	n/a	No OAuth or incremental-scope signals detected.
`tool_snapshot_probe`	OK	n/a	Check completed
`tools_list`	OK	29.3 ms	105 tool(s) exposed
`transport_compliance_probe`	Error	29.0 ms	Issues: missing session id, missing protocol header, bad protocol not rejected (bad protocol=200).
`utility_coverage_probe`	Missing	26.6 ms	No completions evidence; no pagination evidence; tasks missing.

Known versions

1.0.0

Public server reputation

Validation success 7d

1.0

Validation success 30d

1.0

Mean time to recover

n/a

Breaking diffs 30d

Registry drift frequency 30d

Snapshot changes 30d

Benchmark tasks

Benchmark task	Status	Evidence
Discover tools	Passes	`initialize` • OK `tools_list` • OK
Read-only fetch flow	Degraded	`resource_read` • Missing `read_only_tool_surface` • OK
OAuth-required connect	Degraded	`oauth_protected_resource` • Error `step_up_auth_probe` • Missing
Safe write flow with confirmation	Likely to fail	`action_safety_probe` • Error

Utility coverage

Probe status

Missing

Completions

not detected

Completion probe target: none

Pagination

not detected

No nextCursor evidence.

Tasks

Missing

Advertised: no

Tool snapshot diff & changelog

Snapshot changed

Added tools

none

Removed tools

none

Required-argument changes

Tool	Added required args	Removed required args
No required-argument changes detected.

Output-schema drift

Tool	Previous properties	Latest properties
No output-schema drift detected.

Validation diff

Score delta

Summary changed

Tool delta

Prompt delta

Auth mode changed

Write surface expanded

Protocol regressed

Registry drift changed

Regressed checks: none

Improved checks: none

Newly assessed dimensions: none

No longer assessed dimensions: none

Component	Previous	Latest	Delta
No component deltas between the latest two runs.

Registry & provenance divergence

Probe status

Not_Assessed

Direct official match

yes

Drift fields

none

Cross-registry alias disagreements

none

Field	Registry	Live server card
Title	n/a	n/a
Version	n/a	n/a
Homepage	n/a	n/a

Active alerts

No active alerts for the current server state.

Aliases & registry graph

Identifier	Source	Canonical	Identity evidence	Score
`ai.finestructure/fine-structure`	official_registry	yes	canonical	56.2

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

ai.finestructure/fine-structure

Duplicate aliases

Registry sources

official_registry

Remote URLs

https://finestructure.ai/api/mcp

Homepages

none

Source disagreements

Field	What differs	Observed values
No source disagreements detected.

Fix it

Why this score?

Access & Protocol

20/44

Connectivity, auth, and transport expectations for common clients.

Interface Quality

27/56

How well the tool/resource interface communicates and behaves under automation.

Security Posture

20/36

How safely the exposed tool surface handles destructive actions, egress, execution, secrets, and risky inputs.

Reliability & Trust

23/24

Operational stability, consistency, and trustworthiness over time.

Discovery & Governance

14/28

How well the server is documented, listed, and governed in public registries.

Adoption & Market

4/8

Adoption clues and public evidence that the server is intended for external use.

Algorithmic score breakdown

Auth Operability

2/4

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

2/4

Completeness of tool descriptions, parameter docs, examples, and schema shape.

Backward Compatibility

4/4

Stability score across tool schema/name drift relative to prior validations.

SLO Health

4/4

Availability, latency, and burst-failure profile across recent validation history.

Security Hygiene

2/4

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

3/4

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

0/4

Quality of prompt metadata, argument shape, and prompt discoverability for clients.

Resource Contract

0/4

How completely resources and resource templates describe URIs, types, and usage shape.

Discovery Metadata

1/4

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

0/4

Depth and client compatibility of OAuth/OIDC metadata beyond the minimal protected-resource check.

Recovery Semantics

0/4

Whether failures include actionable machine-readable next steps such as retry or upgrade guidance.

Maintenance Signal

4/4

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

0/4

Whether OAuth metadata and WWW-Authenticate challenges support granular, incremental consent instead of broad upfront scopes.

Transport Compliance

0/4

Checks session headers, protocol-version enforcement, session teardown, and expired-session behavior.

Utility Coverage

0/4

Signals support for completions, pagination, and task-oriented utility surfaces that larger clients increasingly expect.

Advanced Capability Coverage

0/4

Coverage of newer MCP surfaces like roots, sampling, elicitation, structured output, and related metadata.

Connector Publishability

2/4

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

4/4

Whether prompts and docs steer users toward safe auth flows instead of pasting secrets directly.

Action Safety

1/4

Risk-weighted view of destructive, exec, egress, and confirmation semantics across the tool surface.

Official Registry Presence

4/4

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

1/4

Assesses arbitrary URL fetch, crawl, webhook, and remote-request exposure on the tool surface.

Execution / Sandbox Safety

1/4

Evaluates shell, code, script, and command-execution exposure and whether that surface appears contained.

Data Exfiltration Resilience

2/4

Assesses export, dump, backup, and bulk-read behavior against the surrounding auth and safeguard signals.

Least Privilege Scope

1/4

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

1/4

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

1.0

Experimental candidate, weight 0. Export and bulk-access evidence only; no impact on totals, verdicts, rankings, or gates.

Actionable remediation

Severity	Remediation	Why it matters	Recommended 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	Expose /.well-known/oauth-protected-resource	Without a protected-resource document, OAuth clients cannot discover auth requirements reliably.	Serve /.well-known/oauth-protected-resource and point it at your authorization server metadata. Playbook Serve `/.well-known/oauth-protected-resource` from the same host as the MCP endpoint. Point it at the authorization server metadata URL. Confirm clients receive consistent auth hints before tool execution.
High	Publish OAuth authorization-server metadata	Clients need authorization-server metadata to discover issuer, endpoints, and DCR support.	Publish /.well-known/oauth-authorization-server from your issuer and include registration_endpoint when supported. Playbook Publish `/.well-known/oauth-authorization-server` from the issuer. Add `registration_endpoint` if DCR is supported. Verify issuer, authorization, token, and jwks metadata are all reachable.
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.
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.
Medium	Document minimal scopes and return cleaner auth challenges	Modern clients expect granular scopes and step-up auth signals such as WWW-Authenticate scope hints.	Return granular scopes and WWW-Authenticate challenge hints instead of forcing overly broad auth upfront. Playbook Advertise the narrowest viable scopes in OAuth metadata. Return `WWW-Authenticate` challenges with scope or insufficient-scope hints when additional consent is needed. Revalidate with both public discovery and auth-required flows.
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	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	Expose modern utility surfaces like completions, pagination, or tasks	Utility coverage improves interoperability with larger clients and long-lived agent workflows.	Expose completions, pagination, and task metadata where supported so larger clients can plan and resume work safely. Playbook Advertise `completions`, pagination cursors, and `tasks` only when they are actually supported. Return `nextCursor` on large list operations when pagination is available. Document task support and whether it requires step-up auth.
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.

Point loss breakdown

Component	Current	Points missing
Utility Coverage	0/4	-4.0
Transport Compliance	0/4	-4.0
Step Up Auth	0/4	-4.0
Resource Contract	0/4	-4.0
Request Association	0/4	-4.0
Recovery Semantics	0/4	-4.0
Prompt Contract	0/4	-4.0
OAUTH Interop	0/4	-4.0
Advanced Capability Coverage	0/4	-4.0
Least Privilege Scope	1/4	-3.0
Execution Sandbox Safety	1/4	-3.0
Error Contract	1/4	-3.0

Compatibility profiles

OpenAI Connectors

55.6

partial (5 of 9 requirements met)

Connector URL: https://finestructure.ai/api/mcp
# No OAuth metadata detected.
# Server: ai.finestructure/fine-structure

Claude Desktop

83.3

compatible (5 of 6 requirements met)

Transport behavior should match Claude-compatible HTTP expectations.

{
  "mcpServers": {
    "fine-structure": {
      "command": "npx",
      "args": ["mcp-remote", "https://finestructure.ai/api/mcp"]
    }
  }
}

Smithery

60.0

partial (3 of 5 requirements met)

Metadata quality should be serviceable.; Machine-readable failure semantics should be present.

smithery mcp add "https://finestructure.ai/api/mcp"

Generic Streamable HTTP

100.0

compatible (6 of 6 requirements met)

No major blockers detected.

curl -sS https://finestructure.ai/api/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): 43.6 • evidence too old to display: ✕

Policy exports

Export policy

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

Verify Hosted MCP

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_production_readiness unsafe_write_action_surface

Deployment	Status	Endpoint	Release
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://finestructure.ai/api/mcp
# No OAuth metadata detected.
# Server: ai.finestructure/fine-structure

Claude Desktop

{
  "mcpServers": {
    "fine-structure": {
      "command": "npx",
      "args": ["mcp-remote", "https://finestructure.ai/api/mcp"]
    }
  }
}

Smithery

smithery mcp add "https://finestructure.ai/api/mcp"

Generic Http

curl -sS https://finestructure.ai/api/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

create_app agency_create_client agency_list_clients agency_create_client_app agency_create_claim_link agency_get_claim_status update_app publish_app

Showing 8 of 105 tools.

Observed from the latest live validation against https://finestructure.ai/api/mcp. This is the target server surface, not Verify's own inspection tools.

Live capability counts

105 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 ai.finestructure/fine-structure.

Direct machine links

JSON report • Compare this server • Verify MCP API

History

Validation history

7 day score delta

n/a

30 day score delta

n/a

Recent healthy ratio

100%

Freshness

1.1h

Timestamp	Status	Score	Latency	Tools
Aug 12, 2026 01:29:55 PM UTC	Healthy	56.2	545.5 ms	105
Aug 12, 2026 01:29:51 AM UTC	Healthy	56.2	1047.0 ms	105
Aug 11, 2026 01:29:22 PM UTC	Healthy	56.8	1309.8 ms	not fetched
Aug 11, 2026 01:23:21 AM UTC	Healthy	56.8	1205.1 ms	not fetched
Aug 10, 2026 01:22:44 PM UTC	Healthy	56.8	972.9 ms	not fetched
Aug 10, 2026 01:22:25 AM UTC	Healthy	56.8	625.5 ms	not fetched
Aug 09, 2026 01:22:05 PM UTC	Healthy	56.2	1187.0 ms	not fetched
Aug 09, 2026 01:21:44 AM UTC	Healthy	56.8	744.0 ms	not fetched

Validation timeline

Validated	Summary	Score	Protocol	Auth mode	Tools	High-risk tools	Changes
Aug 12, 2026 01:29:55 PM UTC	Healthy	56.2	2024-11-05	public	105	3	none
Aug 12, 2026 01:29:51 AM UTC	Healthy	56.2	2024-11-05	public	105	3	none
Aug 11, 2026 01:29:22 PM UTC	Healthy	n/a	unknown	unknown	not fetched	0	none
Aug 11, 2026 01:23:21 AM UTC	Healthy	n/a	unknown	unknown	not fetched	0	none
Aug 10, 2026 01:22:44 PM UTC	Healthy	n/a	unknown	unknown	not fetched	0	none
Aug 10, 2026 01:22:25 AM UTC	Healthy	n/a	unknown	unknown	not fetched	0	none
Aug 09, 2026 01:22:05 PM UTC	Healthy	n/a	unknown	unknown	not fetched	0	none
Aug 09, 2026 01:21:44 AM UTC	Healthy	n/a	unknown	unknown	not fetched	0	none
Aug 08, 2026 01:21:35 PM UTC	Healthy	n/a	unknown	unknown	not fetched	0	none
Aug 08, 2026 01:20:41 AM UTC	Healthy	n/a	unknown	unknown	not fetched	0	none

Recent validation runs

Recent validation runs for this MCP server
Started	Status	Summary	Latency	Checks
Aug 12, 2026 01:29:55 PM UTC	Completed	Healthy	545.5 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 01:29:50 AM UTC	Completed	Healthy	1047.0 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 11, 2026 01:29:20 PM UTC	Completed	Healthy	1309.8 ms	`not fetched (not counted in confidence)`
Aug 11, 2026 01:23:20 AM UTC	Completed	Healthy	1205.1 ms	`not fetched (not counted in confidence)`
Aug 10, 2026 01:22:43 PM UTC	Completed	Healthy	972.9 ms	`not fetched (not counted in confidence)`
Aug 10, 2026 01:22:25 AM UTC	Completed	Healthy	625.5 ms	`not fetched (not counted in confidence)`
Aug 09, 2026 01:22:04 PM UTC	Completed	Healthy	1187.0 ms	`not fetched (not counted in confidence)`
Aug 09, 2026 01:21:43 AM UTC	Completed	Healthy	744.0 ms	`not fetched (not counted in confidence)`
Aug 08, 2026 01:21:35 PM UTC	Completed	Healthy	533.8 ms	`not fetched (not counted in confidence)`
Aug 08, 2026 01:20:40 AM UTC	Completed	Healthy	732.1 ms	`not fetched (not counted in confidence)`

Incident & change feed

Timestamp	Event	Details
Aug 12, 2026 01:29:55 PM UTC	Latest validation: healthy	Score 56.2 with status healthy.
Aug 05, 2026 10:58:19 AM UTC	Score corrected (post-1.0.503 remediation, R1 zero-anchoring)	Prior: 71.31. Corrected: 65.02.

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": 27,
    "items": {
      "action_safety_probe": {
        "auth_present": false,
        "safeguard_count": 16,
        "status": "error"
      },
      "advanced_capabilities_probe": {
        "status": "missing"
      },
      "connector_publishability_probe": {
        "status": "warning"
      },
      "connector_replay_probe": {
        "status": "ok"
      },
      "determinism_probe": {
        "latency_ms": 25.84,
        "status": "ok"
      },
      "initialize": {
        "http_status": 200,
        "latency_ms": 63.38,
        "payload_omitted": true,
        "status": "ok"
      },
      "interactive_flow_probe": {
        "status": "ok"
      },
      "oauth_authorization_server": {
        "reason": "no_authorization_server",
        "status": "missing"
      },
      "oauth_protected_resource": {
        "latency_ms": 60.38,
        "reason": "Non-MCP content type: text/html",
        "status": "error"
      },
      "official_registry_probe": {
        "status": "ok"
      },
      "openid_configuration": {
        "reason": "no_authorization_server",
        "status": "missing"
      },
      "probe_noise_resilience": {
        "http_status": 200,
        "latency_ms": 90.2,
        "status": "ok"
      },
      "prompt_get": {
        "reason": "not_advertised",
        "status": "missing"
      },
      "prompts_list": {
        "http_status": 200,
        "latency_ms": 20.86,
        "payload_omitted": true,
        "reason": "not_supported",
        "status": "missing"
      },
      "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": 200,
        "latency_ms": 21.76,
        "payload_omitted": true,
        "reason": "not_supported",
        "status": "missing"
      },
      "schema_divergence_probe": {
        "reason": "no_server_card_tools",
        "status": "missing"
      },
      "server_card": {
        "latency_ms": 41.53,
        "reason": "Client error '404 Not Found' for url 'https://finestructure.ai/.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": "missing"
      },
      "tool_snapshot_probe": {
        "status": "ok"
      },
      "tools_list": {
        "http_status": 200,
        "latency_ms": 29.34,
        "payload_omitted": true,
        "status": "ok",
        "tool_count": 105,
        "tool_names_preview": [
          "create_app",
          "agency_create_client",
          "agency_list_clients",
          "agency_create_client_app",
          "agency_create_claim_link",
          "agency_get_claim_status",
          "update_app",
          "publish_app",
          "get_platform_guide",
          "get_recommended_workflow",
          "get_job_status",
          "get_app_status",
          "get_app_links",
          "list_app_domains",
          "add_custom_domain",
          "get_domain_verification",
          "check_domain_verification",
          "set_primary_domain",
          "remove_custom_domain",
          "get_domain_ssl_status",
          "configure_domain_redirects",
          "list_apps",
          "get_app_files",
          "read_app_file",
          "read_app_files"
        ]
      },
      "transport_compliance_probe": {
        "latency_ms": 29.02,
        "protocol_header_present": false,
        "status": "error"
      },
      "utility_coverage_probe": {
        "latency_ms": 26.61,
        "status": "missing"
      }
    },
    "omitted_count": 0
  },
  "failures": {
    "count": 5,
    "items": {
      "oauth_authorization_server": {},
      "oauth_protected_resource": {},
      "openid_configuration": {},
      "server_card": {},
      "transport_compliance_probe": {}
    },
    "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://finestructure.ai/api/mcp",
  "server_card": {
    "name": null,
    "raw_payload_omitted": false,
    "version": null
  },
  "server_identifier": "ai.finestructure/fine-structure",
  "truncated": true
}

Capabilities

OAuth: ✕
DCR/CIMD: ✕
Prompts: ✕
Homepage: none
Docs: none
Support: none
Icon: none
Remote endpoint: https://finestructure.ai/api/mcp
Server card: none

Use-case taxonomy

database search communication productivity

Transport compliance drilldown

Probe status

Error

Transport

streamable-http

Session header

Protocol header

Bad protocol response

200

DELETE teardown

n/a

Expired session retry

n/a

Last-Event-ID visible

Issues: missing_session_id, missing_protocol_header, bad_protocol_not_rejected

Request association

Status

Missing

Advertised capabilities

none

Observed idle methods

none

Violating methods

none

Probe HTTP status

n/a

Issues

none

Connector replay

Status

Backward compatible

✓

Would break after refresh

Added tools

none

Removed tools

none

Additive output changes

none

Required-argument replay breaks

Tool	Added required args	Removed required args
No required-argument replay breaks detected.

Output-schema replay breaks

Tool	Removed properties	Added properties
No output-schema replay breaks detected.