API & integrations

Programmatic access to agent-ready.dev scans. Pro subscribers can issue API keys from the dashboard. Three surfaces, one key.

Model Context Protocol (MCP)

Agent Ready is also available as a remote MCP server. Drop it into Claude Desktop, Cursor, Cline, or any MCP-compatible client to run scans inline and query history. Uses the same API key as the REST API.

Claude Desktop supports remote HTTP MCP servers natively. Paste this into claude_desktop_config.json and replace the key with one from your dashboard.

{
  "mcpServers": {
    "agent-ready": {
      "url": "https://agent-ready.dev/api/v1/mcp",
      "headers": {
        "Authorization": "Bearer ar_live_..."
      }
    }
  }
}

Tools available: scan_site(url, pageLimit?), get_scan(id). The server manifest is published at /.well-known/mcp.json.

CI / CD

Gate PRs on Agent Ready scores. The GitHub Action posts a summary comment on every PR and fails the check if the Vercel score drops below a threshold.

Add AGENT_READY_API_KEY as a repo secret (from your dashboard), drop this workflow in, done.

# .github/workflows/scan.yml
name: Agent Ready scan
on:
  pull_request:

jobs:
  scan:
    runs-on: ubuntu-latest
    permissions:
      pull-requests: write
    steps:
      - name: Wait for Vercel preview
        id: preview
        uses: patrickedqvist/wait-for-vercel-preview@v1.3.2
        with:
          token: ${{ secrets.GITHUB_TOKEN }}
          max_timeout: 300

      - name: Agent Ready scan
        uses: mlava/agent-ready@v1
        with:
          api-key: ${{ secrets.AGENT_READY_API_KEY }}
          url: ${{ steps.preview.outputs.url }}
          min-vercel-score: "70"

REST API reference

Interactive OpenAPI reference with a “Try it” console. Opens in a dedicated view. Browse the reference →