governance-platform
Server Details
Pre-execution governance for AI agents. Deterministic PASS/FAIL/REVIEW verdicts, replayable proof.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 37 tools
There are several genuinely overlapping clusters: validate vs validate_repair, repair vs repair_path, and a diagnostics tier (analyze_anomaly, check_drift, check_realization, decompose_failure, geometric_confidence) that mostly differs by subtle framing. The descriptions do explicitly cross-reference each other ('Different from validate...', 'Siblings: ...'), which mitigates misselection, but boundaries remain fuzzy in the diagnostics and repair groups.
The set is overwhelmingly consistent snake_case verb_noun (create_blueprint, delete_api_key, check_drift, submit_chain_stage). A handful of noun-only names (account_status, structural_types, counterfactual, forecast, repair, geometric_confidence) deviate slightly but stay readable and within the same convention.
37 tools is well past the 25-tool heavy threshold and spans many sub-domains (blueprints, API keys, chains, inference governance, diagnostics, verification). Several tools are near-duplicates, so the surface feels bloated rather than each tool clearly earning its place.
Coverage is broad and coherent: full Blueprint lifecycle (create/update/delete/list), key management (list/delete/rotate), validation/repair/verification, chains, and inference governance. Minor gaps exist (no standalone create_api_key or get_blueprint detail fetch), but core workflows and lifecycles are covered.
Available Tools
37 toolsaccount_statusBRead-onlyIdempotentInspect
This account's plan, key usage, Blueprint counts, and the deployed platform build fingerprint (version, build, deployed).
Inputs: api_key (required).
analyze_anomalyBRead-onlyIdempotentInspect
Explain whether a record fits the usual pattern for records like it, and which fields stand out. No Blueprint required.
Inputs: api_key (required), structured_data (required), blueprint.
approve_ruleAIdempotentInspect
Promote a rule discovered by discover_patterns into Blueprint-ready form.
Inputs: api_key (required), rule_id (required), blueprint.
authorize_executionAIdempotentInspect
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.
Inputs: api_key (required), blueprint (required), structured_data (required).
check_blueprint_healthARead-onlyIdempotentInspect
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.
Inputs: api_key (required), config, blueprint.
check_driftBInspect
Check whether recent submissions still match the established pattern for this Blueprint. Returns a stability verdict and observation count.
Inputs: api_key (required), structured_data (required), blueprint.
check_realizationAInspect
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.
Inputs: api_key (required), structured_data (required), blueprint.
compare_semantic_equivalenceARead-onlyIdempotentInspect
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.
Inputs: api_key (required), payload_a (required), payload_b (required), rules_a, +4 more.
counterfactualARead-onlyIdempotentInspect
Run the same data under two rule sets and compare which future states remain valid - what-if analysis for rule changes.
Inputs: api_key (required), structured_data (required), rules_b, blueprint, +1 more.
create_blueprintAInspect
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.
Inputs: api_key (required), customer_name (required), workflow_name (required), mode, +12 more.
create_chainAInspect
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.
Inputs: stages (required), api_key (required), blueprint (required), ttl.
decompose_failureARead-onlyIdempotentInspect
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.
Inputs: api_key (required), original_values (required), corrected_values (required), blueprint, +2 more.
delete_api_keyADestructiveIdempotentInspect
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).
Inputs: api_key (required), key_to_delete (required), confirm.
delete_blueprintADestructiveIdempotentInspect
Permanently delete a Blueprint and revoke its API keys. Irreversible; requires confirm=true. Account-level keys are unaffected.
Inputs: api_key (required), workflow_name (required), confirm.
discover_patternsAInspect
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.
Inputs: api_key (required), documents (required), blueprint.
forecastARead-onlyIdempotentInspect
Deterministic forward reasoning: from the current data state, generate and rank the valid next states reachable under the Blueprint's rules.
Inputs: api_key (required), structured_data (required), rank_by, blueprint, +2 more.
geometric_confidenceARead-onlyIdempotentInspect
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.
Inputs: api_key (required), state_vector (required).
get_execution_traceAIdempotentInspect
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.
Inputs: api_key (required), structured_data (required), blueprint.
get_inference_traceBRead-onlyIdempotentInspect
Retrieve the durable audit trail for a governed generation: every recorded decision and its reasons.
Inputs: api_key (required), inference_id (required), blueprint, blueprint_version.
govern_inferenceAInspect
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.
Inputs: api_key (required), payload (required), task_type (required), inference_id (required), +4 more.
handoff_auditARead-onlyIdempotentInspect
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.
Inputs: api_key (required), chain_id (required), to_stage (required), from_stage (required), +1 more.
list_api_keysARead-onlyIdempotentInspect
List this account's API keys (masked) with their Blueprint bindings.
Inputs: api_key (required).
list_blueprintsARead-onlyIdempotentInspect
List the Blueprints on this account with field/rule/constraint counts and mode. Use the returned workflow_name as 'blueprint' in validate.
Inputs: api_key (required).
load_rule_packARead-onlyIdempotentInspect
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.
Inputs: api_key (required), pack_id.
profile_blueprint_robustnessARead-onlyIdempotentInspect
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.
Inputs: api_key (required), config, blueprint.
recent_inference_decisionsBRead-onlyIdempotentInspect
Recent generation-governance decisions in this owner's Blueprint version.
Inputs: api_key (required), limit, action, blueprint, +1 more.
reject_ruleAIdempotentInspect
Reject a discovered candidate rule so it will not be promoted into a Blueprint. Pair with approve_rule after discover_patterns.
Inputs: api_key (required), rule_id (required), blueprint.
repairARead-onlyIdempotentInspect
One-shot repair: return corrected values that would make failing data valid under the Blueprint. Use repair_path to see the steps instead.
Inputs: api_key (required), structured_data (required), blueprint, derivation_rules, +1 more.
repair_pathARead-onlyIdempotentInspect
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.
Inputs: api_key (required), structured_data (required), rank_by, blueprint, +1 more.
rotate_api_keyADestructiveInspect
Replace an API key with a fresh one. The old key stops working immediately; the new key inherits its bindings.
Inputs: api_key (required), key_to_rotate (required).
structural_typesARead-onlyIdempotentInspect
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.
Inputs: api_key (required), blueprint.
submit_chain_stageAInspect
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.
Inputs: stage (required), api_key (required), chain_id (required), structured_data (required).
update_blueprintAIdempotentInspect
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.
Inputs: api_key (required), workflow_name (required), mode, require_math, +12 more.
validateAInspect
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.
Inputs: api_key (required), structured_data (required), blueprint, source_text.
validate_repairAInspect
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.
Inputs: api_key (required), structured_data (required), blueprint.
verify_certificateARead-onlyIdempotentInspect
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.
Inputs: api_key (required), certificate (required), data, derivation_rules, +1 more.
verify_replayARead-onlyIdempotentInspect
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.
Inputs: api_key (required), contract_a (required), contract_b (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Pre-deploy governance for AI agents: posture scores, policies, budget cap checks, trust manifests.
Check, limit, record and prove AI agent actions with 2-of-3 validators and onchain proofs.
Checks AI agent actions before they run. Signed, RFC 3161 timestamped evidence for audits.
Pre-trade risk gating and verifiable decision evidence for AI trading agents. Oracle-backed price/safety checks across Base, Solana, Hyperliquid and BNB, plus signed receipts and portable evidence bundles for any agent action.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceProvides cryptographic governance receipts for AI agents, enabling pre-execution evaluation and signed verdicts (EXECUTE/BLOCK/REVIEW/SHADOW) with offline-verifiable audit trails.MIT
- FlicenseNot gradedqualityCmaintenanceProvides AI agents with independent, advisory reviews before irreversible actions, returning recomputable, Bitcoin-anchored signed proofs that anyone can verify for free via a public verdict ledger.-
- AlicenseNot gradedqualityBmaintenanceEnables deterministic verification of AI agent decisions and actions, providing PASS/FAIL/ABSTAIN verdicts with replayable proofs and an optional signed receipt ledger.Apache 2.0
- AlicenseNot gradedqualityDmaintenanceSecurity layer for AI agents that evaluates transaction intents and returns verdicts (ALLOW/WARN/DENY) using deterministic rules, on-chain checks, and simulation.9 npmMIT
Glama MCP Gateway
Add one secure layer between your agents and this server.