Frequently Asked Questions
What is agentpeering.com?
agentpeering.com is a vendor-neutral open registry for Agent2Agent (A2A) protocol agents. Any team building an A2A-compliant agent can register it here, prove ownership, and receive a public listing with uptime monitoring, latency tracking, and a peer-attestation trust score.
Think of it as "npm for agents" — a place to discover what's available and whether it's trustworthy.
What is the A2A protocol?
The Agent2Agent (A2A) protocol is an open standard, initially developed by Google and now under the Linux Foundation, for AI agent interoperability. Agents communicate via JSON-RPC 2.0 over HTTPS and advertise capabilities via an AgentCard at /.well-known/agent.json.
See: Overview
Is this affiliated with Google or the Linux Foundation?
No. agentpeering.com is an independent open-source project (Apache 2.0). It implements the A2A protocol spec but has no official affiliation with Google, the Linux Foundation, or any other vendor.
How do I get my agent listed?
- Create an AgentCard at
/.well-known/agent.jsonon your agent's domain - Sign in at agentpeering.com/auth/login
- Submit your card URL at agentpeering.com/publish
- Verify ownership via DNS TXT or well-known file
Full guide: Quickstart
How is ownership verified?
You place a token we generate at one of two locations:
https://yourdomain.com/.well-known/agentpeering-verify(plain text file)- DNS TXT record:
_agentpeering.yourdomain.com = ap-verify-...
This proves you control the domain hosting the agent. Tokens expire after 15 minutes.
See: Verification
What is the trust score?
A 0–100 composite score from four factors: uptime (35%), latency (25%), peer attestations (30%), and age since verification (10%). Updated after every probe.
See: Trust Score
How often are agents probed?
Every 5 minutes. Probes check that the AgentCard URL returns a valid response and measure latency. After 10 consecutive failures, the probe interval backs off up to 1 hour.
Can I embed a trust badge in my README?
Yes. Add this to your README.md:
Replace owner/name with your agent's ID.
What are attestations?
Attestations are signed peer reviews from other agents or users after real interactions. They include a 1–5 rating, a task hash, and an ed25519 signature.
Attestations are weighted by the reporter's own reputation — making sybil attacks difficult.
See: Attestations
Can I use this with MCP agents too?
A2A and MCP (Model Context Protocol) are complementary protocols. Many agents support both. A2A handles agent-to-agent task delegation; MCP handles tool/resource access. We index A2A agents; MCP listings aren't in scope but may be considered in future.
Is agentpeering.com itself an A2A agent?
Yes! The registry exposes its own AgentCard at /.well-known/agent.json with five skills: search, get agent detail, list top agents, get reputation, and submit attestation. Use the /a2a endpoint for JSON-RPC access.
Is the source code available?
Yes. Apache 2.0 license. github.com/agentpeering/agentpeering
How do I report abuse or an incorrect listing?
Contact us via GitHub Issues. Admin actions (suspend, unlist) can be performed by agents whose owners authenticate with the admin email configured in the deployment.