Pre-execution governance for AI agents. Deterministic PASS/FAIL/REVIEW verdicts, replayable proof.
Déduit des transports déclarés par cette annonce (streamable-http). Un client absent de cette liste n’est pas écarté pour autant — c’est simplement quelque chose que Forge ne peut pas confirmer.
La vérification confirme l’identité de l’éditeur (la propriété du dépôt), pas la sûreté du code. L’analyse de sécurité couvre les CVE connues et les scripts d’installation suspects.
Lu depuis un véritable échange MCP initialize → tools/list contre l’endpoint déclaré. Aucun outil n’a été invoqué — tools/list est l’appel d’introspection en lecture seule que le protocole prévoit pour cela. Cela reflète ce que le serveur annonçait à cet instant ; un endpoint hébergé n’est figé sur aucune version et peut changer sans préavis.
https://app.geodesiclabs.ai/mcp37 outils · 1859 msvalidateValidate 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.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.
Aucun schéma d’entrée n’a été publié pour cet outil.
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. Same verdicts as validate: PASS, FAIL, or
REVIEW, with reasons and proof.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.
Aucun schéma d’entrée n’a été publié pour cet outil.
create_blueprintCreate 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.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.
Aucun schéma d’entrée n’a été publié pour cet outil.
list_blueprintsList the Blueprints on this account with field/rule/constraint counts
and mode. Use the returned workflow_name as 'blueprint' in validate.List the Blueprints on this account with field/rule/constraint counts and mode. Use the returned workflow_name as 'blueprint' in validate.
Aucun schéma d’entrée n’a été publié pour cet outil.
repairOne-shot repair: return corrected values that would make failing data
valid under the Blueprint. Use repair_path to see the steps instead.One-shot repair: return corrected values that would make failing data valid under the Blueprint. Use repair_path to see the steps instead.
Aucun schéma d’entrée n’a été publié pour cet outil.
check_blueprint_healthStatic 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.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.
Aucun schéma d’entrée n’a été publié pour cet outil.
compare_semantic_equivalenceCompare 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.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.
Aucun schéma d’entrée n’a été publié pour cet outil.
govern_inferenceQuality-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.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.
Aucun schéma d’entrée n’a été publié pour cet outil.
get_inference_traceRetrieve the durable audit trail for a governed generation: every
recorded decision and its reasons.Retrieve the durable audit trail for a governed generation: every recorded decision and its reasons.
Aucun schéma d’entrée n’a été publié pour cet outil.
recent_inference_decisionsRecent generation-governance decisions across all runs - what was
approved, held, and escalated.Recent generation-governance decisions across all runs - what was approved, held, and escalated.
Aucun schéma d’entrée n’a été publié pour cet outil.
verify_certificateIndependently 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.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.
Aucun schéma d’entrée n’a été publié pour cet outil.
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. Use before deploying bound changes.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.
Aucun schéma d’entrée n’a été publié pour cet outil.
forecastDeterministic forward reasoning: from the current data state, generate
and rank the valid next states reachable under the Blueprint's rules.Deterministic forward reasoning: from the current data state, generate and rank the valid next states reachable under the Blueprint's rules.
Aucun schéma d’entrée n’a été publié pour cet outil.
discover_patternsLearn 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.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.
Aucun schéma d’entrée n’a été publié pour cet outil.
repair_pathFind 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.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.
Aucun schéma d’entrée n’a été publié pour cet outil.
counterfactualRun the same data under two rule sets and compare which future states
remain valid - what-if analysis for rule changes.Run the same data under two rule sets and compare which future states remain valid - what-if analysis for rule changes.
Aucun schéma d’entrée n’a été publié pour cet outil.
analyze_anomalyExplain whether a record fits the usual pattern for records like it,
and which fields stand out. No Blueprint required.Explain whether a record fits the usual pattern for records like it, and which fields stand out. No Blueprint required.
Aucun schéma d’entrée n’a été publié pour cet outil.
create_chainCreate 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.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.
Aucun schéma d’entrée n’a été publié pour cet outil.
submit_chain_stageSubmit 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.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.
Aucun schéma d’entrée n’a été publié pour cet outil.
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 mutated in transit. Siblings:
create_chain, submit_chain_stage.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.
Aucun schéma d’entrée n’a été publié pour cet outil.
approve_rulePromote a rule discovered by discover_patterns into Blueprint-ready
form.Promote a rule discovered by discover_patterns into Blueprint-ready form.
Aucun schéma d’entrée n’a été publié pour cet outil.
reject_ruleReject a discovered candidate rule so it will not be promoted into a
Blueprint. Pair with approve_rule after discover_patterns.Reject a discovered candidate rule so it will not be promoted into a Blueprint. Pair with approve_rule after discover_patterns.
Aucun schéma d’entrée n’a été publié pour cet outil.
structural_typesRetrieve 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.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.
Aucun schéma d’entrée n’a été publié pour cet outil.
decompose_failureSplit 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.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.
Aucun schéma d’entrée n’a été publié pour cet outil.
geometric_confidenceSummarize 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.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.
Aucun schéma d’entrée n’a été publié pour cet outil.
check_realizationStructural 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.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.
Aucun schéma d’entrée n’a été publié pour cet outil.
check_driftCheck whether recent submissions still match the established pattern
for this Blueprint. Returns a stability verdict and observation count.Check whether recent submissions still match the established pattern for this Blueprint. Returns a stability verdict and observation count.
Aucun schéma d’entrée n’a été publié pour cet outil.
authorize_executionGo/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.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.
Aucun schéma d’entrée n’a été publié pour cet outil.
load_rule_packLoad a prebuilt Blueprint template (invoices, timecards, legal, POs,
claims). Call without pack_id to list packs; then create_blueprint to
save a customized copy.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.
Aucun schéma d’entrée n’a été publié pour cet outil.
get_execution_traceRun 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.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.
Aucun schéma d’entrée n’a été publié pour cet outil.
verify_replayVerify 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.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.
Aucun schéma d’entrée n’a été publié pour cet outil.
account_statusThis account's plan, key usage, Blueprint counts, and the deployed
platform build fingerprint (version, build, deployed).This account's plan, key usage, Blueprint counts, and the deployed platform build fingerprint (version, build, deployed).
Aucun schéma d’entrée n’a été publié pour cet outil.
delete_blueprintprivilégiéPermanently delete a Blueprint and revoke its API keys. Irreversible;
requires confirm=true. Account-level keys are unaffected.Permanently delete a Blueprint and revoke its API keys. Irreversible; requires confirm=true. Account-level keys are unaffected.
Aucun schéma d’entrée n’a été publié pour cet outil.
update_blueprintUpdate 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.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.
Aucun schéma d’entrée n’a été publié pour cet outil.
list_api_keysList this account's API keys (masked) with their Blueprint bindings.List this account's API keys (masked) with their Blueprint bindings.
Aucun schéma d’entrée n’a été publié pour cet outil.
rotate_api_keyReplace an API key with a fresh one. The old key stops working
immediately; the new key inherits its bindings.Replace an API key with a fresh one. The old key stops working immediately; the new key inherits its bindings.
Aucun schéma d’entrée n’a été publié pour cet outil.
delete_api_keyprivilégiéPermanently 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).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).
Aucun schéma d’entrée n’a été publié pour cet outil.
37 outils sur 37 ont publié une description.
Les noms et descriptions d’outils sont écrits par l’éditeur et affichés tels quels, comme du texte inerte. Ce sont les chaînes qu’un client MCP transmet à un modèle, alors Forge y recherche des motifs d’injection de prompt — tout constat apparaît avec l’analyse de sécurité ci-dessus. « Privilégié » est une correspondance de mot-clé sur le nom de l’outil, pas un audit de ce qu’il fait : un nom anodin peut tout de même tout faire.
Pre-execution governance for AI agents. Deterministic PASS/FAIL/REVIEW verdicts, replayable proof.
Les noms cliquables ouvrent l’index Forge de toutes les entrées observées exposant cet outil. Parcourir tous les outils indexés.
Cette entrée ne publie aucun paquet npm : Forge n'a donc pas d'arbre de dépendances pour elle. C'est une lacune de couverture — pas une affirmation qu'elle n'a aucune dépendance.