Agent Ready MCP server

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

• scansite** — 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.
• getscan** — 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.
• validatestructureddata — 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, interpretscan, remediationplan. 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: scansite, ask, and validatestructureddata all work anonymously out of the box (scansite 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/claudedesktopconfig.json (macOS) or %APPDATA%\Claude\claudedesktopconfig.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

Shortened. The full README is on GitHub.