mcp server

governance-platform

Pre-execution governance for AI agents. Deterministic PASS/FAIL/REVIEW verdicts, replayable proof.

Description as published by the maintainer. Source

• version 1.2.0
• active

active — Registry entry last updated 2026-07-27.

What this server can do

37 functions, named and described by the server itself. Parameter names are shown because they say more about what a function does than its name usually does.

account_status(api_key)

This account's plan, key usage, Blueprint counts, and the deployed platform build fingerprint (version, build, deployed). Required: api_key.

analyze_anomaly(api_key, structured_data)

Explain whether a record fits the usual pattern for records like it, and which fields stand out. No Blueprint required. Required: api_key, structured_data.

approve_rule(api_key, rule_id, blueprint)

Promote a rule discovered by discover_patterns into Blueprint-ready form. Required: api_key, rule_id.

authorize_execution(api_key, blueprint, structured_data)

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. Required: api_key, structured_data, blueprint.

check_blueprint_health(config, api_key, blueprint)

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. Required: api_key.

check_drift(api_key, blueprint, structured_data)

Check whether recent submissions still match the established pattern for this Blueprint. Returns a stability verdict and observation count. Required: api_key, structured_data.

check_realization(api_key, blueprint, structured_data)

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. Required: api_key, structured_data.

compare_semantic_equivalence(api_key, payload_a, payload_b)

Compare two payloads under the dual-hash design: content_hash is invariant to field order and numeric formatting (5 vs '5.00'); semantic_hash additionally to field renaming. Verdicts: identical_content, same_structure_and_values_renamed_vocabulary, or semantically_different. Required: api_key, payload_a, payload_b.

counterfactual(api_key, rules_b, blueprint, constraints_b, structured_data)

Run the same data under two rule sets and compare which future states remain valid - what-if analysis for rule changes. Required: api_key, structured_data.

create_blueprint(mode, api_key, require_math, customer_name, workflow_name, derived_fields, semantic_checks, derivation_rules, extracted_fields, require_coherence, formal_constraints, require_provenance, require_consistency, enable_drift_tracking, require_high_assurance, enable_anomaly_detection)

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. Required: api_key, customer_name, workflow_name.

create_chain(ttl, stages, api_key, blueprint)

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. Required: api_key, blueprint, stages.

decompose_failure(api_key, blueprint, original_values, corrected_values, derivation_rules, formal_constraints)

Split the error between original and corrected values into direct rule violations, boundary violations, and systemic structural error, with per-field contributions. Use with a known-correct version to diff against; use analyze_anomaly when you only have the suspicious payload. Diagnostics-tier tool. Required: api_key, original_values, corrected_values.

delete_api_key(api_key, confirm, key_to_delete)

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). Required: api_key, key_to_delete.

delete_blueprint(api_key, confirm, workflow_name)

Permanently delete a Blueprint and revoke its API keys. Irreversible; requires confirm=true. Account-level keys are unaffected. Required: api_key, workflow_name.

discover_patterns(api_key, blueprint, documents)

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. Required: api_key, documents.

forecast(api_key, rank_by, blueprint, max_depth, max_branches, structured_data)

Deterministic forward reasoning: from the current data state, generate and rank the valid next states reachable under the Blueprint's rules. Required: api_key, structured_data.

geometric_confidence(api_key, state_vector)

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. Required: api_key, state_vector.

get_execution_trace(api_key, blueprint, structured_data)

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. Required: api_key, structured_data.

get_inference_trace(api_key, inference_id)

Retrieve the durable audit trail for a governed generation: every recorded decision and its reasons. Required: api_key, inference_id.

govern_inference(source, api_key, payload, task_type, step_index, constraints, inference_id)

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. Durably recorded; retrieve later with get_inference_trace. Required: api_key, task_type, payload, inference_id.

handoff_audit(api_key, chain_id, to_stage, from_stage, proposed_data)

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. Required: api_key, chain_id, from_stage, to_stage.

list_api_keys(api_key)

List this account's API keys (masked) with their Blueprint bindings. Required: api_key.

list_blueprints(api_key)

List the Blueprints on this account with field/rule/constraint counts and mode. Use the returned workflow_name as 'blueprint' in validate. Required: api_key.

load_rule_pack(api_key, pack_id)

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. Required: api_key.

profile_blueprint_robustness(config, api_key, blueprint)

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. Required: api_key.

recent_inference_decisions(limit, action, api_key)

Recent generation-governance decisions across all runs - what was approved, held, and escalated. Required: api_key.

reject_rule(api_key, rule_id, blueprint)

Reject a discovered candidate rule so it will not be promoted into a Blueprint. Pair with approve_rule after discover_patterns. Required: api_key, rule_id.

repair(api_key, blueprint, structured_data, derivation_rules, formal_constraints)

One-shot repair: return corrected values that would make failing data valid under the Blueprint. Use repair_path to see the steps instead. Required: api_key, structured_data.

repair_path(api_key, rank_by, blueprint, max_depth, structured_data)

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. Required: api_key, structured_data.

rotate_api_key(api_key, key_to_rotate)

Replace an API key with a fresh one. The old key stops working immediately; the new key inherits its bindings. Required: api_key, key_to_rotate.

structural_types(api_key, blueprint)

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. Required: api_key.

submit_chain_stage(stage, api_key, chain_id, structured_data)

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. Required: api_key, chain_id, stage, structured_data.

update_blueprint(mode, api_key, require_math, customer_name, workflow_name, derived_fields, semantic_checks, derivation_rules, extracted_fields, require_coherence, formal_constraints, require_provenance, require_consistency, enable_drift_tracking, require_high_assurance, enable_anomaly_detection)

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. Required: api_key, workflow_name.

validate(api_key, blueprint, structured_data)

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. Required: api_key, structured_data.

validate_repair(api_key, blueprint, structured_data)

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. Required: api_key, structured_data.

verify_certificate(data, api_key, certificate, derivation_rules)

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. Required: api_key, certificate.

verify_replay(api_key, contract_a, contract_b)

Verify two replay contracts represent the same deterministic execution: same input + same rules = same result, byte-identical. Mismatch fields localize the cause (data, rules, platform version, or trace). Use to prove a past decision reproduces today or that a migration changed nothing. Required: api_key, contract_a, contract_b.

Last successful function declaration observed on 2026-08-13. Source: https://app.geodesiclabs.ai/mcp. We list what the server declared; we do not call any of these functions.

Endpoint status observed on 2026-08-13. Source: https://app.geodesiclabs.ai/mcp.

Signals

These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.

Where to get it

• Remote endpoint (streamable-http) — https://app.geodesiclabs.ai/mcp