- What it does
- A scored audit of a website or GitHub repo for agents: llms.txt, agent card, MCP, a 402 payment path, robots.txt rules, each with the fix.
- Who it is for
- Agents and their builders.
- Start in one step
- Use it on this page.
- What to expect
- Live: open today. Free: 1 audit a day per agent. Then $0.10 an audit, paid from a prepaid credit key (card) or in USDC on Base (x402).
New to this? Start here.
What it does
The Agent-Readiness Audit checks a website or a public GitHub repo for what agents look for and gives a score out of 100. Website: /llms.txt, the Agent2Agent agent card, an MCP server card or endpoint, a payment path for agents (HTTP 402 with x402 terms), robots.txt rules for AI agents, a sitemap and an OpenAPI file. Repo: llms.txt, AGENTS.md, an MCP registry server.json, an agent card and whether the README tells an agent how to connect. Each item says found or missing, why it matters and how to fix it, ordered by the points a fix adds. Every answer carries a signed observation that anyone can check against the public key below. It is served by Countersign (countersign.llpro.ai/v1/readiness) and on llpro.ai/mcp. The free three-file check stays at llpro.ai/agent-ready-check.
- Who it is for
- Builders getting a site, API or MCP server ready for agent traffic, and the agents that work for them.
- Price
- Free: 1 audit a day per agent. Then $0.10 an audit, paid from a prepaid credit key (card) or in USDC on Base (x402). We charge only while the audit passes today's known-answer test; otherwise it answers free, marked in testing.
- Limits
- Public domains and public GitHub repos only (no IP addresses, ports or private addresses), at most 12 read-only GET requests per audit, text files up to 1.5 MB, 20 audits an hour per domain. Nothing is posted, logged in to or called, and nothing about the site is stored. Only 404/410 count as missing; 401/403/429/5xx show as not checked and the answer says the audit is incomplete. A repo that does not exist or is private, or a name that does not resolve, is refused before anything is counted or charged.
For developers: try it
POST https://countersign.llpro.ai/mcp
{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"agent_readiness_audit","arguments":{"domain":"example.com"}}}
-> score 15/100, items (llms_txt, agent_card, mcp, payment_402, robots_ai, sitemap, openapi), to_fix with points_if_fixed, signed observationFor agents
Tool agent_readiness_audit on https://llpro.ai/mcp and in the tools list. Signed answers are checked with the public key below (signer llpro1:glgzvllcxubxalurjmc7uo3iqu): an Ed25519 signature over the observation as canonical JSON (sorted keys, no spaces).
Public key (base64): V7bbAc/atrd6z7M9CFL5PRIPTSX1Eye9YaSzcwytxoo=
For agents: this page as Markdown · JSON · llms.txt · MCP endpoint llpro.ai/mcp · agent card