AI Agent Readiness — Integrate in 60 seconds

Scan any public URL against 27 agent-readiness checks across 6 categories. Free. No auth. Available via REST, GET one-liner, and MCP.

Try it

Web UI →

REST API

curl -sX POST https://www.startuphub.ai/api/agent-readiness/scan \
  -H 'Content-Type: application/json' \
  -d '{"url":"https://your-site.com"}'

Or GET:

curl 'https://www.startuphub.ai/api/agent-readiness/scan?url=https://your-site.com'

Rate limit: 10 scans / 10 min / IP. No auth.

MCP (Claude Desktop, Cursor, Windsurf)

Add this to your MCP config:

{
  "mcpServers": {
    "startuphub-agent-readiness": {
      "command": "npx",
      "args": ["mcp-remote", "https://www.startuphub.ai/api/v1/mcp"]
    }
  }
}

Then prompt your agent:

“Call the scan_agent_readiness tool on https://example.com and tell me the top 3 fixes.”

Discovery card: /.well-known/mcp/server-card.json

Response shape

{
  "total_score": 72,
  "grade": "B",
  "categories": [
    { "category": "discoverability", "score": 100, ... },
    { "category": "content",         "score":  60, ... },
    ...
  ],
  "checks": [
    { "id": "robots_txt", "status": "pass", "title": "robots.txt present", ... },
    ...
  ],
  "extras": {
    "tokens_html":     53201,
    "tokens_markdown": 12740,
    "token_savings_pct": 76,
    "ttfb_ms": 145,
    "wins":       ["MCP Server Card — <0.01% of sites have one"],
    "weaknesses": ["Markdown content negotiation", "llms.txt guide"]
  },
  "markdown_summary": "# Agent-Readiness Report..."
}

What we check

  • Discoverability: robots.txt, sitemap, Link header (RFC 8288)
  • Content: markdown content negotiation, llms.txt, llms-full.txt
  • Access control: AI bot rules, Content Signals, Web Bot Auth
  • Capabilities: MCP (a /.well-known/mcp/server-card.json or a live remote MCP server at mcp.<domain>/mcp, detected via the mcp-session-id handshake), API Catalog (RFC 9727), OpenAPI spec, Agent Skills, OAuth discovery (RFC 8414 + 9728), agentic registration
  • Commerce: x402 Payment Required (apex /x402, x402.<domain> subdomains, and <brand>mpp.dev gateways), MPP machine payments (Tempo / Stripe), Agent Payments discovery (AP2 / ACP), x402-mesh participation, Offer / Product structured data, agent-reachable payment link, commerce surface
  • Quality: OpenGraph, JSON-LD structured data, RateLimit headers (RFC 9331), security.txt, JSON content negotiation

Payment and MCP detection is not limited to the apex well-known paths. The scanner also probes dedicated subdomains (x402.<domain>, mcp.<domain>), hosted gateways (<brand>mpp.dev), and, when nothing is found directly, follows the links in your own homepage / llms.txt / docs to confirm a live endpoint with a 402 or MCP initialize probe. So an x402 or MCP server hosted off the apex still scores.

Get notified when we add checks

New checks, MCP tools, and endpoints land regularly. Subscribe to the API changelog RSS feed to be updated automatically.

Each failing check returns a fix prompt

Paste straight into Claude Code / Cursor / Windsurf / Copilot. No rewriting.

Run a scan →