AI agent readability scanner — score any public URL against the Vercel Agent Readability Spec, llmstxt.org, and 6 agent-protocol manifests (MCP, A2A, agents.json, agent-permissions, UCP, x402). 59 checks with per-check fix guidance. Same engine as agent-ready.dev.
概要
Agent Ready is an AI agent readability scanner — point it at any public URL and get back a 0–100 score plus per-check remediation hints for every failing check. This MCP server wraps the same engine that powers agent-ready.dev, so Claude Desktop, Claude Code, Cursor, Cline, VS Code, and Windsurf can run scans inline and explain the results.
59 checks across 4 spec families
- 38 against the Vercel Agent Readability Spec — 15 site-wide checks (llms.txt, robots.txt, sitemap.xml, AGENTS.md, HTTPS, OpenAPI) plus 23 per-page checks (metadata, JSON-LD, markdown mirrors, content negotiation, JS-rendering, code-block language tags).
- 10 against the llmstxt.org specification.
- 11 against agent-protocol manifests: MCP Server Cards (SEP-1649 / RFC 9728), A2A Agent Cards (a2a.proto v1.0.0), Wildcard agents.json, agent-permissions.json, UCP, x402 Payment Required.
Every failing check ships with a concrete howToFix string — no generic "consider adding metadata" messages.
What the server exposes
| Kind | Name | Purpose |
|---|---|---|
| tool | scan_site | Run a fresh scan against a URL. |
| tool | get_scan | Fetch a previous scan by id. |
| prompt | scan | Fresh scan + summary. |
| prompt | interpret_scan | Plain-English explanation of a scan's findings. |
| prompt | remediation_plan | Prioritised fix-it doc (optional focus: "seo" or "agents"). |
| skill | agent-ready | Claude Skill descriptor for activation routing. |
Quick install (Claude Desktop / Claude Code / Cursor / Cline)
{
"mcpServers": {
"agent-ready": {
"command": "npx",
"args": ["-y", "agent-ready-mcp@latest"],
"env": {
"AGENT_READY_API_KEY": "ar_live_..."
}
}
}
}
Issue a Pro API key from the dashboard. The MCP server requires Pro or Team tier — free-tier scans are available through the web UI only.
Also available on
- GitHub: mlava/agent-ready-mcp
- npm: agent-ready-mcp
- Smithery: agent-ready/agent-ready-mcp
- MCP registry: io.github.mlava/agent-ready-mcp
- Hosted Streamable HTTP:
https://agent-ready.dev/api/v1/mcp(Bearer auth) - Full install guide: agent-ready.dev/mcp
サーバー設定
{
"mcpServers": {
"agent-ready": {
"command": "npx",
"args": [
"-y",
"agent-ready-mcp@latest"
],
"env": {
"AGENT_READY_API_KEY": "<YOUR_AGENT_READY_API_KEY>"
}
}
}
}