Scan a public website for AI agent-readability against the Vercel Agent Readability Spec, llmstxt.org, and agent-protocol manifests. Returns a 0–100 score, the llms.txt score, and the top failing checks with a link to the full per-check report.
Agent Ready source site3 tools on this site
What this tool does
Scan a public website for AI agent-readability against the Vercel Agent Readability Spec, llmstxt.org, and agent-protocol manifests. Returns a 0–100 score, the llms.txt score, and the top failing checks with a link to the full per-check report. Use it on Agent Ready with an agent. It runs in the browser on the website and needs no package install.
How to install
Open the agent-ready.dev website and ask your browser agent to use scan_site
Run with an agent
Use the scan_site tool on agent-ready.dev with url: <string>. Return the structured result and cite the source page.
Input contract
urlstringThe public URL to scan, e.g. the linked page
Verify the live listing at the source before a production call. Fields marked as a starter contract may differ from what the site expects.