getstackrun

ai agents agent oversight revocation audit log mcp

STACK runs between AI agents and the systems they use. Each agent works under a short-lived Passport that states what it may do. STACK checks every call against that Passport, records suspicious behavior, can deny configured actions and writes each decision to a hash-chained audit log. This connector brings the oversight side of STACK into the conversation. With it you can: - list your agents, their permissions and any that are blocked - see active Passports and revoke one, every Passport for an agent, or all of them - decide flagged Passport checkouts waiting for review - open, complete or revoke Missions and see what an agent did inside one - read the audit log, verify its hash chain and export signed records - list security events, adjust detector and PII-redaction settings, and scan text for prompt injection - manage notification rules, inbound webhooks, drop-offs and fleets - check usage A revocation applies to the agent's next call through STACK and cascades to any Passports it delegated. The connector does not call third-party services, connect or display credentials, issue Passports or run paid skills. Those stay in the STACK Console, the CLI and STACK's full MCP endpoint. Sign-in uses OAuth, and a token issued to this connector is refused by the full endpoint. STACK's application services run in Stockholm and its database runs in Frankfurt. Requires a STACK account with at least one registered agent. Setup: https://getstack.run/docs/mcp-setup#directory