Pre-execution governance for AI agents. Deterministic PASS/FAIL/REVIEW verdicts, replayable proof.
by ai.geodesiclabsv1.2.0
Observed by Wellknown
Evidence
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
30-day availability1/1 checks ok
30 days agotoday
Endpoints
https://app.geodesiclabs.ai/mcpmcp streamable http · checked on a schedule
Registry facts
Not distributed through a package registry we index.
when
check
result
http
latency
detail
5 h ago
mcp initialize
ok
200
335 ms
server GeodesicAI 1.27.0 · protocol 2025-06-18 · 37 tools
Tools observed via MCP handshake
validate — Validate structured data against a Blueprint's rules BEFORE the result
is used. Returns PASS, FAIL, or REVIEW with plain-language findings,
repair sugge
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
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
list_blueprints — List the Blueprints on this account with field/rule/constraint counts
and mode. Use the returned workflow_name as 'blueprint' in validate.
repair — One-shot repair: return corrected values that would make failing data
valid under the Blueprint. Use repair_path to see the steps instead.
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 unsatis
compare_semantic_equivalence — Compare two payloads under the dual-hash design: content_hash is
invariant to field order and numeric formatting (5 vs '5.00');
semantic_hash additional
govern_inference — Quality-govern an in-progress AI generation step BEFORE its output is
used (complements validate, which checks finished documents). Returns
an action -
get_inference_trace — Retrieve the durable audit trail for a governed generation: every
recorded decision and its reasons.
recent_inference_decisions — Recent generation-governance decisions across all runs - what was
approved, held, and escalated.
verify_certificate — Independently re-verify a validation certificate. Integrity mode checks
the hash chain; full mode (certificate + original data) recomputes
every atteste
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
Declared by sources
What the publisher says
Attributed to the source that supplied each field. Treated as claims, not facts.
No long description beyond the summary.
kind ← Official MCP Registry
name ← Official MCP Registry
summary ← Official MCP Registry
version ← Official MCP Registry
description ← Official MCP Registry
publisherName ← Official MCP Registry
Derived by Wellknown
Capabilities
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
6 h ago · declared · summary → "Pre-execution governance for AI agents. Deterministic PASS/FAIL/REVIEW verdicts, replayable proof."
6 h ago · declared · description → "Pre-execution governance for AI agents. Deterministic PASS/FAIL/REVIEW verdicts, replayable proof."
6 h ago · declared · publisherName → "ai.geodesiclabs"
6 h ago · declared · version → "1.2.0"
6 h ago · declared · protocols → ["mcp"]
forecast — Deterministic forward reasoning: from the current data state, generate
and rank the valid next states reachable under the Blueprint's rules.
discover_patterns — Learn candidate validation rules and structural document types from a
batch of your records, deterministically - no Blueprint required.
Promote results
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-
counterfactual — Run the same data under two rule sets and compare which future states
remain valid - what-if analysis for rule changes.
analyze_anomaly — Explain whether a record fits the usual pattern for records like it,
and which fields stand out. No Blueprint required.
create_chain — Create a multi-agent sequential chain: stages validate in order against
one Blueprint, repairs propagate forward, TTL bounds the run. Siblings:
submit_c
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 accumula
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 verd
approve_rule — Promote a rule discovered by discover_patterns into Blueprint-ready
form.
reject_rule — Reject a discovered candidate rule so it will not be promoted into a
Blueprint. Pair with approve_rule after discover_patterns.
structural_types — Retrieve the document categories a discover_patterns session identified
(counts, distinguishing fields, domain hints). Read-only; returns
status=no_sess
decompose_failure — Split the error between original and corrected values into direct rule
violations, boundary violations, and systemic structural error, with
per-field co
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 che
check_realization — Structural realization analysis of a payload against the Blueprint's
reference configuration (requires a 'realization' block; otherwise
status=skipped).
check_drift — Check whether recent submissions still match the established pattern
for this Blueprint. Returns a stability verdict and observation count.
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;
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 custom
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
verify_replay — Verify two replay contracts represent the same deterministic execution:
same input + same rules = same result, byte-identical. Mismatch fields
localize
account_status — This account's plan, key usage, Blueprint counts, and the deployed
platform build fingerprint (version, build, deployed).
delete_blueprint — Permanently delete a Blueprint and revoke its API keys. Irreversible;
requires confirm=true. Account-level keys are unaffected.
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 wo
list_api_keys — List this account's API keys (masked) with their Blueprint bindings.
rotate_api_key — Replace an API key with a fresh one. The old key stops working
immediately; the new key inherits its bindings.
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 w