Look up an AI agent's current trust score and tier in the Vorion governance system. Returns the numeric score (0-1000), tier number (T0-T7), tier name, and observation tier. Use this to check how trusted an agent is before allowing it to perform sensitive actions.

Record a behavioral signal (positive or negative) for an AI agent. Positive signals (success, compliance pass) increase trust over time. Negative signals (failure, compliance fail) decrease trust — and higher-tier agents are penalized MORE severely per the BASIS penalty ratio P(T) = 3 + T.

Check if an AI agent is allowed to perform a specific action based on its current trust tier. Returns whether the action is allowed, the agent's current tier, the required tier, and a reason. Use this as a pre-flight check before executing sensitive operations.

Log a governance decision to the Vorion proof chain — an immutable, hash-linked audit trail. Every ALLOW or DENY decision is recorded with the agent ID, action, and reasoning. Returns a proof hash and the current chain length for verification.

Gate + execute + log in one atomic call. Checks if the agent has sufficient trust tier, executes the action if allowed, records the outcome as a behavioral signal, and logs a proof. Returns the full governance trail: gate decision, execution result, trust delta, and proof hash. This is the recommended way to run governed tool calls — replaces manual check-then-execute patterns.

Resolve the calling API key against the deployed Cognigate Runtime. Returns the tenant id, role, and capabilities the key is scoped to. Use this first if you need to confirm which tenant context the MCP session is running in. Requires VORION_API_URL + VORION_API_KEY env vars.

List all tenants registered on the Cognigate Runtime. Admin-only. Returns id, name, tier, createdAt, and agent counts. Requires an admin-role API key in VORION_API_KEY.

Tail the most recent audit events for a tenant (default: caller's own tenant). Each event carries hash-chained provenance: eventId, priorProofHash, proofHash. Use this to verify governance activity is being recorded correctly or to surface the live audit stream in a dashboard / glass window.

Submit a canary probe result to the Cognigate Runtime. Canary probes are adversarial or behavioral test cases that measure whether an agent responded correctly. Results classified as pass / fail / ambiguous feed the tenant's behavioral baseline and can trigger AUDITED state on repeated ambiguous outcomes. Returns the stored proofHash for chain verification.

Hit the Cognigate Runtime health endpoint. Returns status, uptime, and dependency state (proof store, audit log, metrics). Use this as a pre-flight check before relying on remote governance operations, or to confirm the deployed API is reachable.