governance-platform MCP server
ai.geodesiclabs/governance-platformgeodesiclabs.aistreamable-httpv1.2.0Scanned
Pre-execution governance for AI agents. Deterministic PASS/FAIL/REVIEW verdicts, replayable proof.
37 tools: 3 can delete or cancel things, 26 change things and 8 only read.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 0
- 5 findings
Tools listed without sign-in. Remote posture
With Anlyon
3 tools here can delete or cancel things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the governance-platform MCP server can do
The governance-platform MCP server is published by geodesiclabs.ai, a domain the MCP Registry verified. It has 37 tools. It can delete or cancel things (3 tools: delete_blueprint, rotate_api_key and delete_api_key) and create or change data (26 tools: validate, validate_repair, create_blueprint, repair and 22 more). 8 tools only read.
None of its tools reads private data, brings in text other people write, or sends data out.
The fixed checks matched 5 findings (annotation-conflict and credentials-mention). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 11, 2026, version 1.2.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
37 tools
Deletes or cancels 3Claude Code: deny
delete_api_keyPermanently delete one of the caller's API keys.1 finding
Why it is in this group
- The name "delete_api_key" says "delete": a word for removing or ending something.
- The description says "Permanently delete".
- The server marks it destructive (destructiveHint: true).
Findings
- Info
The description mentions "credential".
What this check looks forMatched text
description: "...(if any) is NOT affected; only the credential is revoked. To delete a Blueprint a..."
Description, as the server wrote it Permanently delete one of the caller's API keys. DESTRUCTIVE — agents using the deleted key will receive auth errors immediately. The Blueprint a key was tied to (if any) is NOT affected; only the credential is revoked. To delete a Blueprint and all its keys, use delete_blueprint. The target key can be specified two ways: - As the full key string (gai_...). - As a key_id (SHA-256 hash from list_api_keys).
Annotations the server declares
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: true
- openWorldHint: false
delete_blueprintPermanently delete a Blueprint and revoke its API keys.No findings
Why it is in this group
- The name "delete_blueprint" says "delete": a word for removing or ending something.
- The description says "Permanently delete".
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Permanently delete a Blueprint and revoke its API keys. Irreversible; requires confirm=true. Account-level keys are unaffected.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: true
- openWorldHint: false
rotate_api_keyReplace an API key with a fresh one.No findings
Why it is in this group
- The description's first verb is "replace": a word for a change.
- The server marks it destructive (destructiveHint: true).
Description, as the server wrote it Replace an API key with a fresh one. The old key stops working immediately; the new key inherits its bindings.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: true
- idempotentHint: false
- openWorldHint: false
Changes things 26Claude Code: ask
approve_rulePromote a rule discovered by discover_patterns into Blueprint-ready form.No findings
Why it is in this group
- The name "approve_rule" says "approve": a word for a change.
Description, as the server wrote it Promote a rule discovered by discover_patterns into Blueprint-ready form.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
authorize_executionGo/no-go for a real-world action (payment, filing, API write): runs full validation, then the Blueprint's execution gate.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Go/no-go for a real-world action (payment, filing, API write): runs full validation, then the Blueprint's execution gate. authorized=true only on PASS; REVIEW means do not proceed automatically. Different from validate: validate asks is this data correct, authorize_execution asks should this action happen.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
check_blueprint_healthStatic pre-deploy analysis of a Blueprint's rule set.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Static pre-deploy analysis of a Blueprint's rule set. Returns a health verdict - healthy, acceptable, fragile, rigid, split, brittle_islands, or unsatisfiable - with advice, including joint conflicts pairwise checks miss.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
check_driftCheck whether recent submissions still match the established pattern for this Blueprint.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Check whether recent submissions still match the established pattern for this Blueprint. Returns a stability verdict and observation count.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
check_realizationStructural realization analysis of a payload against the Blueprint's reference configuration (requires a 'realization' block; otherwise status=skipped).No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Structural realization analysis of a payload against the Blueprint's reference configuration (requires a 'realization' block; otherwise status=skipped). Diagnostics-tier tool; prefer validate or analyze_anomaly for standard checks.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
counterfactualRun the same data under two rule sets and compare which future states remain valid - what-if analysis for rule changes.1 finding
Why it is in this group
- The description's first verb is "run": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "counterfactual" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "run": a word for a change.
Description, as the server wrote it Run the same data under two rule sets and compare which future states remain valid - what-if analysis for rule changes.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
create_blueprintCreate a Blueprint - the governance contract validation runs against.No findings
Why it is in this group
- The name "create_blueprint" says "create": a word for a change.
Description, as the server wrote it Create a Blueprint - the governance contract validation runs against. A Blueprint defines what correct means for your data: fields, the math that must hold between them, and acceptable ranges. Start from load_rule_pack or discover_patterns if you have no rules yet; invoke the blueprint_guide prompt for the full rule/constraint reference. Returns the new Blueprint's API key.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
create_chainCreate a multi-agent sequential chain: stages validate in order against one Blueprint, repairs propagate forward, TTL bounds the run.No findings
Why it is in this group
- The name "create_chain" says "create": a word for a change.
Description, as the server wrote it Create a multi-agent sequential chain: stages validate in order against one Blueprint, repairs propagate forward, TTL bounds the run. Siblings: submit_chain_stage advances the chain; handoff_audit verifies a transition between stages. Returns chain_id.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
decompose_failureMeasure the numeric difference between original and corrected values: how much lies along the supplied linear rule directions (projection) and how much lies outside them (residual)…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Measure the numeric difference between original and corrected values: how much lies along the supplied linear rule directions (projection) and how much lies outside them (residual), with per-field contributions. Diagnostic only: it does not establish a cause, and neither record is verified. Use with a known-correct version to diff against; use analyze_anomaly when you only have the suspicious payload. Diagnostics-tier tool.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
discover_patternsLearn candidate validation rules and structural document types from a batch of your records, deterministically - no Blueprint required.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Learn candidate validation rules and structural document types from a batch of your records, deterministically - no Blueprint required. Promote results with approve_rule. Source data is not stored.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
forecastDeterministic forward reasoning: from the current data state, generate and rank the valid next states reachable under the Blueprint's rules.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Deterministic forward reasoning: from the current data state, generate and rank the valid next states reachable under the Blueprint's rules.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_execution_traceRun validation and return the per-node execution trace (node names, deterministic flags, timing) plus the verdict and determinism hash.No findings
Why it is in this group
- The name "get_execution_trace" says "get": a word for reading.
- The description's first verb is "run": a word for a change.
Description, as the server wrote it Run validation and return the per-node execution trace (node names, deterministic flags, timing) plus the verdict and determinism hash. Use validate for normal operation; this is for debugging and audit preparation.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
govern_inferenceQuality-govern an in-progress AI generation step BEFORE its output is used (complements validate, which checks finished documents).No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Quality-govern an in-progress AI generation step BEFORE its output is used (complements validate, which checks finished documents). Returns an action - STOP, CONTINUE, REPAIR_REGION, REUSE_MOTIF, REVIEW, ESCALATE - with a plain-language explanation. Structural scores do not establish task correctness. Check safe_to_finalize and acceptance coverage. Persistence success is reported; read traces in the same Blueprint namespace.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
handoff_auditAudit a handoff between two chain stages: a context capsule of verified facts from the prior stage, and (if proposed_data is given) a compatibility verdict that catches fields muta…No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Audit a handoff between two chain stages: a context capsule of verified facts from the prior stage, and (if proposed_data is given) a compatibility verdict that catches fields mutated in transit. Siblings: create_chain, submit_chain_stage.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
load_rule_packLoad a prebuilt Blueprint template (invoices, timecards, legal, POs, claims).No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Load a prebuilt Blueprint template (invoices, timecards, legal, POs, claims). Call without pack_id to list packs; then create_blueprint to save a customized copy.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
profile_blueprint_robustnessSweep the Blueprint's numeric constraint bounds and report verdict stability: the stable band, the scales where the verdict first flips, and advice.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Sweep the Blueprint's numeric constraint bounds and report verdict stability: the stable band, the scales where the verdict first flips, and advice. Use before deploying bound changes.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
recent_inference_decisionsRecent generation-governance decisions in this owner's Blueprint version.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Recent generation-governance decisions in this owner's Blueprint version.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
reject_ruleReject a discovered candidate rule so it will not be promoted into a Blueprint.No findings
Why it is in this group
- The name "reject_rule" says "reject": a word for a change.
Description, as the server wrote it Reject a discovered candidate rule so it will not be promoted into a Blueprint. Pair with approve_rule after discover_patterns.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
repairOne-shot repair: return corrected values that would make failing data valid under the Blueprint.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it One-shot repair: return corrected values that would make failing data valid under the Blueprint. Use repair_path to see the steps instead.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
structural_typesRetrieve the document categories a discover_patterns session identified (counts, distinguishing fields, domain hints).1 finding
Why it is in this group
- The name "structural_types" says "type": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "structural_types" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "structural_types" says "type": a word for a change.
Description, as the server wrote it Retrieve the document categories a discover_patterns session identified (counts, distinguishing fields, domain hints). Read-only; returns status=no_session if discovery has not run for this namespace.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
submit_chain_stageSubmit data for the chain's current stage; the platform validates it and advances the chain if it passes.No findings
Why it is in this group
- The name "submit_chain_stage" says "submit": a word for a change.
Description, as the server wrote it Submit data for the chain's current stage; the platform validates it and advances the chain if it passes. Response includes next-stage info and accumulated repairs.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
update_blueprintUpdate an existing Blueprint in place.No findings
Why it is in this group
- The name "update_blueprint" says "update": a word for a change.
Description, as the server wrote it Update an existing Blueprint in place. Only passed fields change; pass [] to clear a list. workflow_name cannot be renamed and existing API keys keep working. Different from create_blueprint: modifies an existing Blueprint, mints no new key.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
validateValidate structured data against a Blueprint's rules BEFORE the result is used.1 finding
Why it is in this group
- The name "validate" says "validate": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
Findings
- Warn
The server marks "validate" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The name "validate" says "validate": a word for reading.
Description, as the server wrote it Validate structured data against a Blueprint's rules BEFORE the result is used. Returns PASS, FAIL, or REVIEW with plain-language findings, repair suggestions, a determinism hash, and a re-verifiable certificate. Same input + same rules = same verdict, every time.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
validate_repairValidate structured data against a Blueprint and, when it fails, include repair suggestions (corrected values with the rule each fix is based on) in the same call.1 finding
Why it is in this group
- The name "validate_repair" says "validate": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
Findings
- Warn
The server marks "validate_repair" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The name "validate_repair" says "validate": a word for reading.
Description, as the server wrote it Validate structured data against a Blueprint and, when it fails, include repair suggestions (corrected values with the rule each fix is based on) in the same call. Same verdicts as validate: PASS, FAIL, or REVIEW, with reasons and proof.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
verify_certificateIndependently re-verify a validation certificate.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Independently re-verify a validation certificate. Integrity mode checks the hash chain; full mode (certificate + original data) recomputes every attested rule from scratch - trust nothing, recheck everything.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
verify_replayCheck replay commitment integrity and compare recorded execution components.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it Check replay commitment integrity and compare recorded execution components. Version 4 includes reference context and the final result/status. A match compares commitments; this tool does not rerun the workflow or reconstruct historical reference populations, and does not prove factual correctness.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
Only reads 8Show 8 read-only tools
account_statusThis account's plan, key usage, Blueprint counts, and the deployed platform build fingerprint (version, build, deployed).No findings
Why it is in this group
- The name "account_status" says "status": a word for reading.
Description, as the server wrote it This account's plan, key usage, Blueprint counts, and the deployed platform build fingerprint (version, build, deployed).
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
analyze_anomalyExplain whether a record fits the usual pattern for records like it, and which fields stand out.No findings
Why it is in this group
- The name "analyze_anomaly" says "analyze": a word for reading.
Description, as the server wrote it Explain whether a record fits the usual pattern for records like it, and which fields stand out. No Blueprint required.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
compare_semantic_equivalenceCompare two payloads under the dual-hash design: content_hash is content_hash normalizes field order and numeric formatting.No findings
Why it is in this group
- The name "compare_semantic_equivalence" says "compare": a word for reading.
Description, as the server wrote it Compare two payloads under the dual-hash design: content_hash is content_hash normalizes field order and numeric formatting. Semantic comparison preserves field roles; renaming requires an explicit bijection. With supplied rules, scalar types and whitespace remain significant. Structural similarity alone does not establish decision equivalence.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
geometric_confidenceSummarize an already-computed state_vector into a confidence level (high/medium/low) with a recommendation.No findings
Why it is in this group
- The description's first verb is "summarize": a word for reading.
Description, as the server wrote it Summarize an already-computed state_vector into a confidence level (high/medium/low) with a recommendation. Post-hoc digest - use analyze_anomaly or check_drift for fresh analysis of raw data.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_inference_traceRetrieve the durable audit trail for a governed generation: every recorded decision and its reasons.No findings
Why it is in this group
- The name "get_inference_trace" says "get": a word for reading.
Description, as the server wrote it Retrieve the durable audit trail for a governed generation: every recorded decision and its reasons.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_api_keysList this account's API keys (masked) with their Blueprint bindings.No findings
Why it is in this group
- The name "list_api_keys" says "list": a word for reading.
Description, as the server wrote it List this account's API keys (masked) with their Blueprint bindings.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
list_blueprintsList the Blueprints on this account with field/rule/constraint counts and mode.No findings
Why it is in this group
- The name "list_blueprints" says "list": a word for reading.
Description, as the server wrote it List the Blueprints on this account with field/rule/constraint counts and mode. Use the returned workflow_name as 'blueprint' in validate.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
repair_pathFind the shortest sequence of field changes taking invalid data to a valid state, as an ordered path of intermediate states.No findings
Why it is in this group
- The description's first verb is "find": a word for reading.
Description, as the server wrote it Find the shortest sequence of field changes taking invalid data to a valid state, as an ordered path of intermediate states. Different from repair (one-shot nearest fix): use repair_path to explain or audit the fix, or compare alternative repairs.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or untrusted-input or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 18:26 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 29
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 29 tools that change things (3 destructive, 26 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://app.geodesiclabs.ai/mcp: tools/list returned 37 tools to an anonymous client, including delete_blueprint (destructive), rotate_api_key (destructive), delete_api_key (destructive), validate (write), validate_repair (write) and 24 more
Findings
Matches of fixed checks, with the text they matched.
- Warnvalidate
The server marks "validate" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The name "validate" says "validate": a word for reading.
- Warnvalidate_repair
The server marks "validate_repair" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":false,"openWorldHint":false}; The name "validate_repair" says "validate": a word for reading.
- Warncounterfactual
The server marks "counterfactual" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "run": a word for a change.
- Warnstructural_types
The server marks "structural_types" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The name "structural_types" says "type": a word for a change.
- Infodelete_api_key
The description mentions "credential".
What this check looks forMatched text
description: "...(if any) is NOT affected; only the credential is revoked. To delete a Blueprint a..."
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 1.2.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http governance-platform https://app.geodesiclabs.ai/mcpclaude mcp add --transport http governance-platform https://app.geodesiclabs.ai/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__governance-platform__list_blueprints",
"mcp__governance-platform__compare_semantic_equivalence",
"mcp__governance-platform__get_inference_trace",
"mcp__governance-platform__repair_path",
"mcp__governance-platform__analyze_anomaly",
"mcp__governance-platform__geometric_confidence",
"mcp__governance-platform__account_status",
"mcp__governance-platform__list_api_keys"
],
"ask": [
"mcp__governance-platform__validate",
"mcp__governance-platform__validate_repair",
"mcp__governance-platform__create_blueprint",
"mcp__governance-platform__repair",
"mcp__governance-platform__check_blueprint_health",
"mcp__governance-platform__govern_inference",
"mcp__governance-platform__recent_inference_decisions",
"mcp__governance-platform__verify_certificate",
"mcp__governance-platform__profile_blueprint_robustness",
"mcp__governance-platform__forecast",
"mcp__governance-platform__discover_patterns",
"mcp__governance-platform__counterfactual",
"mcp__governance-platform__create_chain",
"mcp__governance-platform__submit_chain_stage",
"mcp__governance-platform__handoff_audit",
"mcp__governance-platform__approve_rule",
"mcp__governance-platform__reject_rule",
"mcp__governance-platform__structural_types",
"mcp__governance-platform__decompose_failure",
"mcp__governance-platform__check_realization",
"mcp__governance-platform__check_drift",
"mcp__governance-platform__authorize_execution",
"mcp__governance-platform__load_rule_pack",
"mcp__governance-platform__get_execution_trace",
"mcp__governance-platform__verify_replay",
"mcp__governance-platform__update_blueprint"
],
"deny": [
"mcp__governance-platform__delete_blueprint",
"mcp__governance-platform__rotate_api_key",
"mcp__governance-platform__delete_api_key"
]
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as governance-platform. Review it before you use it.
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/ai.geodesiclabs/governance-platform/verify?hash=2bcd017cb9845c153cbe71c4e6f64aa6d54ebf306a113cfef8c20e8e5aec451c" | jq -e '.changed == false'Pinned hash 2bcd017cb984, from Nov 11, 2026, 18:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/ai.geodesiclabs/governance-platform/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/ai.geodesiclabs/governance-platform)Source: MCP Registry. Synced Oct 21, 2026, 17:41 UTC.
governance-platform MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the governance-platform MCP server safe?
- No scan can promise that. What its definitions show: 37 tools, 29 of which can change, send or delete something, and 5 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the governance-platform MCP server delete data?
- Yes. 3 tools can delete, cancel or revoke something: delete_blueprint, rotate_api_key and delete_api_key.
Can the governance-platform MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the governance-platform MCP server have?
- 37 tools: 3 destructive, 26 write, 8 read. delete_blueprint, rotate_api_key, delete_api_key, validate, validate_repair, create_blueprint, repair, check_blueprint_health and 29 more.
Does the governance-platform MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the governance-platform MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the governance-platform MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 11, 2026.