Protection

Simulate gateway evaluation against the protection card

Phase-5 deferred stub — does not evaluate anything. Protection simulation depends on the dedicated protection-policy evaluator, which is not built yet. This endpoint returns a fixed shape: allowed: "conditional" with protection_evaluator_pending_phase_5 in conditions and warn sub-verdicts, for ANY request body. It never calls the policy engine, so the caller-supplied-tool union and the fail-closed empty-union behaviour documented on /v1/alignment/agent/{agent_id}/simulate (MNE-5820) do NOT apply here. Use the alignment simulate endpoint for real governance signals.

post/protection/agent/{agent_id}/simulate

Request

  • Base URL: https://api.mnemom.ai/v1
  • URL: https://api.mnemom.ai/v1/protection/agent/{agent_id}/simulate
  • Auth: one of:
    • HTTP bearer
    • API key in header X-Mnemom-Api-Key
    • API key in cookie mnemom_session

Path parameters

agent_idstring required

Agent identifier (e.g. smolt-abc123)

Request body

Response

Simulation result.

oktrue required
resource'protection' required
allowed'true' | 'false' | 'conditional' required
conditionsstring[] required
suggestionsstring[] required
evaluated_atstring date-time required

Changes

No recorded changes to this operation across all 1 revision of this API.