agent-ready-mcp

MCP server for Agent Ready — scan any URL for AI agent readability against the Vercel Agent Readability Spec, the llmstxt.org standard, and agent-protocol manifests (MCP server cards, A2A, agents.json, agent-permissions.json, UCP, x402, NLWeb). 72 checks across four spec families — 40 site and page checks (15 site-wide + 25 per-page), 10 against llmstxt.org, and 22 against agent-protocol manifests — each with per-check fix guidance, plus a separate accessibility sub-score from 23 WCAG 2.2 / layout-stability checks.

Hosted at https://agent-ready.dev/api/v1/mcp (Streamable HTTP); this package is a thin stdio wrapper around the same REST endpoints, distributed via npm for local MCP clients (Claude Desktop, Claude Code, Cursor, VS Code, Windsurf).

Features

• scan_site — fresh agent-readability scan on any URL. Works without a key on the anonymous free tier (3 scans/30 days per IP, 25-page depth, synchronous); with a Pro key it scans up to 250 pages, polling the hosted API up to 60s.
• get_scan — fetch a previously-run scan by id (Pro key required — scan history is account-scoped).
• ask — natural-language (NLWeb) search over Agent Ready's own methodology, checks, and specs. Public, no API key required; returns Schema.org-typed results.
• validate_structured_data — validate a page's (or a pasted) JSON-LD against Agent Ready's structured-data checks. Public, no API key required; paste mode needs no network, so an agent can check JSON-LD it just authored.
• Three discovery prompts — scan, interpret_scan, remediation_plan. End-to-end workflows from URL → score → fix-it plan.
• SKILL.md — Claude Skill descriptor included under skills/agent-ready/ for activation routing.

Setup

No key is required to start: scan_site, ask, and validate_structured_data all work anonymously out of the box (scan_site on the free anonymous quota — 3 scans per 30 days per IP at 25-page depth). An Agent Ready Pro API key unlocks 50 scans/month, 250-page depth, scan history (get_scan), and weekly monitoring — sign up at agent-ready.dev and issue a key from the dashboard. The env block in the configs below is optional; omit it to run keyless.

Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

{
  "mcpServers": {
    "agent-ready": {
      "command": "npx",
      "args": ["-y", "agent-ready-mcp@latest"],
      "env": {
        "AGENT_READY_API_KEY": "ar_live_..."
      }
    }
  }
}

Claude Code

claude mcp add agent-ready \
  -e AGENT_READY_API_KEY=ar_live_... \
  -- npx -y agent-ready-mcp@latest

Cursor / VS Code / Windsurf

.cursor/mcp.json, .vscode/mcp.json, or ~/.codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "agent-ready": {
      "command": "npx",
      "args": ["-y", "agent-ready-mcp@latest"],
      "env": {
        "AGENT_READY_API_KEY": "ar_live_..."
      }
    }
  }
}

Environment variables

Tools

Prompts

Example workflow

You: Use agent-ready to scan https://my-saas.com
Claude: [calls scan_site] Your site scored 78/100 (Good) on the Vercel Agent
        Readability Spec. The top 3 fixes: …
You: Can you build me a remediation plan?
Claude: [calls remediation_plan with the scan id] Here's the prioritised list…

Skill (Anthropic Claude Skills)

A SKILL.md lives at skills/agent-ready/SKILL.md inside the package. To use it in Claude Desktop / Claude Code, copy the skills/agent-ready/ directory into ~/.claude/skills/.

The skill describes when to activate (URL + readability-audit intent), which tool to pick, how to surface scan results without dumping raw JSON, and when to defer to other tools (general SEO, performance profiling, code editing).

How it works

This package is a thin stdio→HTTPS wrapper:

MCP client (stdio) ↔ agent-ready-mcp ↔ HTTPS ↔ agent-ready.dev/api/v1/scans

All scan execution, persistence, and Pro-tier quota enforcement happen on the hosted server. The npm package only translates between MCP JSON-RPC over stdio and the REST API.

If you'd rather use the hosted MCP server directly (Streamable HTTP transport, no local install), point your MCP client at https://agent-ready.dev/api/v1/mcp with Authorization: Bearer ar_live_....

Methodology

The 72 checks, their weights, and the score formula are documented at agent-ready.dev/methodology. Both manifest.json and server.json in this repo conform to the relevant registry schemas (Glama Marketplace v0.3 and MCP registry 2025-12-11 respectively).

Development

npm install
npm run build       # → dist/mcp-server.mjs
npm test
npm run typecheck

Releasing

See RELEASE.md. It is the source of truth for version surfaces, local checks, tag pushing, the GitHub Actions release workflow, and the manual post-release steps.

License

MIT — see LICENSE.