Dependency-probe-gated exit execution with hash-verified extraction and signed receipts.
Scored across 5 tools
Each tool has a distinct action: execute performs the exit, probe checks dependencies, rejoin_check tests re-procurement blocking, sweep is a portfolio operation, and verify_receipt validates signatures. The boundary between probe and rejoin_check (both are pre-flight checks) is the only mild overlap, but descriptions differentiate them.
All five tools share the exit_ prefix followed by a snake_case action/suffix (exit_execute, exit_probe, exit_rejoin_check, exit_sweep, exit_verify_receipt). The pattern is predictable and readable throughout.
Five tools is well-scoped for a focused exit/deprovisioning workflow, with each tool earning its place across the probe-execute-verify lifecycle.
The surface covers the core exit lifecycle (probe, execute, verify, rejoin check, portfolio sweep). Minor gaps remain: no tool to list/inspect past or in-progress exits, nor to cancel an ongoing exit, but these are workable around.
Execute an exit in the proven order; returns the signed receipt. Metered like the HTTP exit (trial/plan rails only via MCP; paid rails use the HTTP endpoint with x402).
Inputs: service_id (required), mode.
Dependency probe: SAFE-TO-EXIT / DEPENDENTS-FOUND.
Inputs: service_id (required).
Check whether a COMPLETE exit receipt blocks re-procuring a service.
Inputs: scope (required), service_id (required).
Portfolio unused-service sweep (Operator plan).
Inputs: no named parameters.
Verify an exit receipt's signature.
Inputs: receipt (required).
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Cryptographically anchored evidence for agents: verified run receipts, proof-gated settlement.
Governed MCP: agent audit, provenance, deterministic checks, and receipt-backed FragGate execution.
Reviewed public-data search and execution with provenance and verifiable integrity receipts.
Bounded authorization and independently verifiable execution evidence for agents.
Add one secure layer between your agents and this server.
