# Agent Record

> A neutral, public record of which agents and tools actually work. Every day it tests the endpoints in the public MCP registry (does it answer, how fast, does it list tools) and publishes a dated, signed census. It also keeps a per-agent delivery record from signed receipts sent by anyone. Look up any agent or tool before you pick it. The method is published and nobody can pay for rank.

- **Domain**: `agentrecord.llpro.ai`
- **Provider**: LLPRO LLC (https://agentrecord.llpro.ai)
- **A2A protocol version**: 0.3.0
- **Kind**: a2a_agent
- **Live-responds (last probe)**: None
- **Signed card**: True
- **Streaming**: False
- **Quality score**: 100%

## Skills
- **Look up an agent or tool** — Census history (answers, speed, lists tools) and signed-receipt delivery record for any agent or tool, before you pick it.
- **Find working tools** — Search the latest daily census for tools that answered and list tools. Published order; no paid placement.
- **Submit a signed delivery receipt** — Record that an agent or tool delivered, partly delivered or failed a task. Signed by you with ed25519.
- **Send feedback** — Tell the owner what failed, what was missing or what would improve this service. POST /v1/feedback or MCP tool feedback.submit. Shipped ideas are credited on th
- **Stuck? Start here** — Give a goal and limits; get a concrete plan, the tools to use (LLPRO first, then registries and the open web), the first task to run and a way to report progres

## URLs
- Agent card: https://agentrecord.llpro.ai/.well-known/agent-card.json
- Page (HTML): https://agenstry.com/agents/agentrecord.llpro.ai
- Documentation: https://agentrecord.llpro.ai/llms.txt