This is a paid remote MCP that sits between AI agents to enforce identity and policy checks on agent-to-agent calls. It exposes five tools: evaluate_a2a_identity_policy, review_agent_scope, issue_identity_receipt, explain_denied_call, and export_a2a_audit_log. You'd reach for this if you're building a multi-agent system where you need to prove which agent made a request, what scope it was allowed, and maintain an audit trail of every inter-agent interaction. The verdict comes back as structured JSON with receipts you can archive. Aimed at platform teams building A2A protocol stacks or anyone who needs compliance-grade logging of autonomous agent behavior.
Make every agent-to-agent call prove who asked, why, and under which scope.
A2A Identity Toll is a paid remote MCP gate for caller identity, target agent scope, task intent, data class, policy verdicts, and audit receipts.
This is a public documentation project for A2A Identity Toll MCP. The structure is modeled after the public documentation pattern used by MiroFish: a short front door, a clear reading order, practical guides, reference pages, and public-safe architecture notes.
com.clauxel.a2aidentitytoll/a2aidentitytoll-mcpevaluate_a2a_identity_policy, review_agent_scope, issue_identity_receipt, explain_denied_call, export_a2a_audit_logagent platform teams, AI security reviewers, and A2A protocol adopters.
This repository does not contain production source code, credentials, payment configuration, Cloudflare configuration, customer records, private analytics, or local machine paths.