No user-submitted related servers found.
Scored across 16 tools
The surface splits cleanly into minting, gating, and read-only oversight views, and core pairs like verify_receipt vs. get_receipt_evidence or mint_action_receipt vs. mint_receipt_for_record_change are distinguishable. However nine tools (inspect_oversight_case, propose_role_question, get_intervention_evidence, compare_qualification_change, export_acceptance_pack, get_receipt_evidence, get_decision_evidence, replay_decision, propose_requalification) carry nearly identical boilerplate descriptions differing only by domain object, and pairs like get_decision_evidence vs. replay_decision or propose_requalification vs. compare_qualification_change have fuzzy boundaries. An agent can misselect among these without careful reading.
Every tool follows a snake_case verb_noun pattern (verify_receipt, mint_action_receipt, gate_decision, run_exit_drill, export_acceptance_pack). The only minor idiosyncrasy is the first-person 'my' in audit_my_agent_inventory, which does not break the convention.
At 16 tools the server sits at the heavy end for its purpose, with a large block of near-identical read-only evidence views that each add a narrow slice of surface. Several could plausibly be collapsed into a parameterized evidence/readout tool without losing capability.
The surface covers minting, verification, gating, evidence readouts, egress checks, and drills, which is broad lifecycle coverage for a trust/receipt domain. But there is no discovery or listing of existing cases, receipts, or permits, no revocation or key-rotation operations, and inventory audit explicitly cannot enumerate, so agents must supply everything themselves and have no lookup path.