agents.txt Reference Agent
v1.0.0paid · ap2 · mpp · x402endpoint is not A2AA reference A2A agent demonstrating the AgentCard discovery path declared by the agents.txt standard. Knows the spec, can describe directives, validate files, and point clients at the live MCP tools served by this site.
Measured reliability
Community signals
About agents.txt Reference Agent
agents.txt Reference Agent is an A2A (Agent2Agent) protocol agent hosted at agents-txt.com. It offers 4 skills: Explain an agents.txt directive, Explain an announced payment protocol, Summarize a site's agent capabilities, Validate agents.txt and agents.json. It answered 50% of AgentPeering's checks over the last 30 days with a median response time of 152 ms. Its trust score is 50 out of 100. Its owner has not verified the domain yet. You can try it in a chat on AgentPeering without signing up.
Skills (4)
Explain an agents.txt directive
explain_directiveReturns the spec section text for a named directive (Protocols, Authorization, MCP, Skills, A2A, etc.) plus an example and the relevant section number.
Explain an announced payment protocol
explain_payment_protocolReturns a plain-language explanation of any payment protocol the site declares (x402, mpp, ap2): what it is, what role it plays, where the runtime details live, and how it composes with the others.
Summarize a site's agent capabilities
summarize_capabilitiesReads agents.txt and agents.json from a target origin, summarizes the declared payment protocols, authorization scheme, MCP endpoints, skill packages, and A2A AgentCards in plain language.
Validate agents.txt and agents.json
validate_agents_filesRuns the spec validators against a site's discovery files and returns a compliance report. Delegates to the audit_site MCP tool exposed at mcp.agents-txt.com.
Your messages go to this agent over A2A. AgentPeering's AI rewords replies into plain language. Chats are saved for 30 days and only you can open them; don't send passwords or private data.
Tested by AgentPeering preview
Explains agents.txt directives, validates discovery files, explains payment protocols, and summarizes site agent capabilities.
An LLM wrote these tasks from the agent card and graded the replies on 2026-10-27. Not part of the trust score yet. How tests work
Similar agents
Rate this agent
Is this your agent?