Pre-execution governance for AI agents. Deterministic PASS/FAIL/REVIEW verdicts, replayable proof.
| Endpoint | https://app.geodesiclabs.ai/mcp (streamable-http) |
|---|---|
| Registry version | 1.2.0 |
| Now | 37 tools · grade C (69) · pin ts_4e6b15509921ea1d08fe1dee4419fb8d · protocol 2025-06-18 |
| First / last listed | 2026-10-25 00:03 UTC / 2026-10-25 00:03 UTC |
| Grade over time | 2026-10-25: C (69), 37 tools |
Is this your server? Own a server? ToolFit hosted watch re-checks it every 24 h ($0.25 per 30 days) or 6 h ($0.60) and sends you an HMAC-signed webhook when its tools or grade change: POST https://api.youraitools.co/toolfit/v1/watch. To opt out, see About & opt-out.
Tools: validate validate_repair create_blueprint list_blueprints repair check_blueprint_health compare_semantic_equivalence govern_inference get_inference_trace recent_inference_decisions verify_certificate profile_blueprint_robustness forecast discover_patterns repair_path counterfactual analyze_anomaly create_chain submit_chain_stage handoff_audit approve_rule reject_rule structural_types decompose_failure geometric_confidence check_realization check_drift authorize_execution load_rule_pack get_execution_trace verify_replay account_status delete_blueprint update_blueprint list_api_keys rotate_api_key delete_api_key
validate | 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.
params: api_key*, structured_data*, blueprint, source_text |
validate_repair | 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.
params: api_key*, structured_data*, blueprint |
create_blueprint | 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.
params: api_key*, customer_name*, workflow_name*, mode, extracted_fields, derived_fields, derivation_rules, formal_constraints, semantic_checks, require_math, require_consistency, require_coherence, require_provenance, require_high_assurance, enable_anomaly_detection, enable_drift_tracking |
list_blueprints | List the Blueprints on this account with field/rule/constraint counts
and mode. Use the returned workflow_name as 'blueprint' in validate.
params: api_key* |
repair | One-shot repair: return corrected values that would make failing data
valid under the Blueprint. Use repair_path to see the steps instead.
params: api_key*, structured_data*, derivation_rules, formal_constraints, blueprint |
check_blueprint_health | 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.
params: api_key*, blueprint, config |
compare_semantic_equivalence | 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.
params: api_key*, payload_a*, payload_b*, field_mapping, rules_a, rules_b, constraints_a, constraints_b |
govern_inference | 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 report params: api_key*, task_type*, payload*, inference_id*, constraints, source, step_index, blueprint |
get_inference_trace | Retrieve the durable audit trail for a governed generation: every
recorded decision and its reasons.
params: api_key*, inference_id*, blueprint, blueprint_version |
recent_inference_decisions | Recent generation-governance decisions in this owner's Blueprint version.
params: api_key*, limit, action, blueprint, blueprint_version |
verify_certificate | 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.
params: api_key*, certificate*, data, derivation_rules, formal_constraints |
profile_blueprint_robustness | 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.
params: api_key*, blueprint, config |
forecast | Deterministic forward reasoning: from the current data state, generate
and rank the valid next states reachable under the Blueprint's rules.
params: api_key*, structured_data*, blueprint, max_depth, max_branches, rank_by |
discover_patterns | 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.
params: api_key*, documents*, blueprint |
repair_path | 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.
params: api_key*, structured_data*, blueprint, max_depth, rank_by |
counterfactual | Run the same data under two rule sets and compare which future states
remain valid - what-if analysis for rule changes.
params: api_key*, structured_data*, blueprint, rules_b, constraints_b |
analyze_anomaly | Explain whether a record fits the usual pattern for records like it,
and which fields stand out. No Blueprint required.
params: api_key*, structured_data*, blueprint |
create_chain | 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.
params: api_key*, blueprint*, stages*, ttl |
submit_chain_stage | 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.
params: api_key*, chain_id*, stage*, structured_data* |
handoff_audit | 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.
params: api_key*, chain_id*, from_stage*, to_stage*, proposed_data |
approve_rule | Promote a rule discovered by discover_patterns into Blueprint-ready
form.
params: api_key*, rule_id*, blueprint |
reject_rule | Reject a discovered candidate rule so it will not be promoted into a
Blueprint. Pair with approve_rule after discover_patterns.
params: api_key*, rule_id*, blueprint |
structural_types | 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.
params: api_key*, blueprint |
decompose_failure | 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 params: api_key*, original_values*, corrected_values*, derivation_rules, formal_constraints, blueprint |
geometric_confidence | 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.
params: api_key*, state_vector* |
check_realization | 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.
params: api_key*, structured_data*, blueprint |
check_drift | Check whether recent submissions still match the established pattern
for this Blueprint. Returns a stability verdict and observation count.
params: api_key*, structured_data*, blueprint |
authorize_execution | 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.
params: api_key*, structured_data*, blueprint* |
load_rule_pack | 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.
params: api_key*, pack_id |
get_execution_trace | 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.
params: api_key*, structured_data*, blueprint |
verify_replay | 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.
params: api_key*, contract_a*, contract_b* |
account_status | This account's plan, key usage, Blueprint counts, and the deployed
platform build fingerprint (version, build, deployed).
params: api_key* |
delete_blueprint | Permanently delete a Blueprint and revoke its API keys. Irreversible;
requires confirm=true. Account-level keys are unaffected.
params: api_key*, workflow_name*, confirm |
update_blueprint | 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.
params: api_key*, workflow_name*, customer_name, mode, extracted_fields, derived_fields, derivation_rules, formal_constraints, semantic_checks, require_math, require_consistency, require_coherence, require_provenance, require_high_assurance, enable_anomaly_detection, enable_drift_tracking |
list_api_keys | List this account's API keys (masked) with their Blueprint bindings.
params: api_key* |
rotate_api_key | Replace an API key with a fresh one. The old key stops working
immediately; the new key inherits its bindings.
params: api_key*, key_to_rotate* |
delete_api_key | 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 params: api_key*, key_to_delete*, confirm |
Entries describe changes in tool definitions. They are not statements about a server, its quality or its author. The grade measures how the tool definitions fit model providers (token cost, schema compatibility, confusable names) as scored by the ToolFit engine at the time of the listing. JSON: append .json. Opt-out: how or hello@youraitools.co.