mcpwatch

← All servers

Grade B

ai.geodesiclabs/governance-platform

ai.geodesiclabs/governance-platform · v1.2.0 · score 89/100 · checked 2026-11-22

Automated, read-only signal from public data, not an audit or an accusation. Maintainers can dispute any finding. How grading works

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

Findings

SeverityRuleDetail
LowMW005Remote endpoint lists 37 tool(s) to anyone, no credentials needed.
MediumMW1022 tool(s) can execute commands or delete data (delete_blueprint, delete_api_key). Require confirmation before the agent calls them.

What was checked

Public 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

Maintainer? Add the badge

Grades refresh daily. Think a finding is wrong? Dispute this grade.

[![mcpwatch](https://www.mcpwatch.io/badge/ai-geodesiclabs-governance-platform-03b2151c.svg)](https://www.mcpwatch.io/s/ai-geodesiclabs-governance-platform-03b2151c)