
This server brings AI governance and compliance tooling directly into Claude through MCP. It implements GATRI trust scoring to evaluate AI system reliability, provides kill-switch functionality for emergency shutdowns, and includes EU AI Act compliance checks. The repository is early stage with minimal documentation, but the premise is clear: if you're building regulated AI applications or need audit trails and safety controls baked into your Claude workflows, this gives you programmatic access to governance primitives. Expect trust score calculations, compliance validation endpoints, and emergency override controls. Best suited for teams in healthcare, finance, or EU markets where AI Act requirements aren't optional.
MCP-native governance and action-assurance primitives for autonomous AI.
gatri_trust_score — legacy composite trust scoring.assure_action — evidence-backed, context-aware assurance for one agent action.decide_action — converts GATRI assurance + policy + permissions + context into ALLOW, RESTRICT, REQUIRE_HUMAN, or DENY.risk_assessment — deployment risk assessment.compliance_check — EU AI Act-oriented policy check.kill_switch — emergency stop directive.agent × action × context × evidence
↓
GATRI
↓
Vector Decisions
↓
ALLOW / RESTRICT /
REQUIRE_HUMAN / DENY
The important primitive is action assurance, not a generic claim that an agent is safe. The same agent can be acceptable for one action and unacceptable for another.
npm install
npm run build
npm start
The server uses stdio transport and is intended to be consumed by MCP-compatible clients.
Version 1.1.0. This is a protocol-oriented V0: deterministic local evaluation first; evidence ingestion, persistent assurance records, policy registries, signed attestations and remote APIs are subsequent layers.