Agentic Interaction Trust Gate

Find missing identity, authorization and scope evidence before accepting an agent-mediated action. 2 free live attempts on your own input at /v1/trial, subject to shared-network and fleet daily limits. Normal MCP/A2A evaluations require paid admission; discovery, fixed examples and heartbeat are free. Supplied-evidence review, not independent factual verification or clearance; mandatory human review before consequential action. Caller must invoke and enforce the result in its integration. Zero-trust evidence review for agent-to-agent interactions: before a counterparty agent transacts or invokes a capability, check what identity and authority evidence is present. An A2A-compatible evidence-readiness gate for agent-to-agent and agent-mediated actions across A2A endpoint, MCP tool, checkout, account, and API surfaces. Bring the actor's identity claim, target surface, requested action, and dated evidence; get trust-routing triage, the missing source categories, evidence gaps, watch-next indicators, a decision-readiness score, a trust signal, and human-review routing. Evidence-readiness only — not identity verification, authentication, or transaction authorization.

Skills

• Counterparty-agent trust gate
  Turns an unknown counterparty agent's requested action, target surface, identity claim, and dated evidence into a structured trust-routing recommendation — allow, step up, escalate to human review, or block until verified — with the evidence that is still missing, a decision-readiness score, and mandatory human-review routing. Evidence-readiness triage, not identity verification. Evaluation requires structured JSON; see the request schema and A2A example in the card extension.
  agentic-aia2aagent-to-agentcounterparty-agentmcptrust-and-safetyevidence-readinesshuman-review
• Delegated authority and scope evidence gaps
  Lists missing principal authorization, tool-scope and session evidence for the proposed action. Supplied references do not authenticate the actor or grant authority.
  delegationtool-scopeevidence-gapssupplied-evidencehuman-review
• Agent-action human-review handoff
  Returns the readiness label, triage recommendation and review packet for the requested action. The consuming integration must enforce its own permissions and human approval.
  human-reviewagent-to-agentreadinesssupplied-evidencehuman-review

How to call

https://interaction-trust.agendamcp.dpdns.org/message/send

Listed in

Directories this entry was found in.