Do I need all of these?

No. Most are brand new and almost no sites have them. Start with markdown. Add MCP or an API catalog only if agents could usefully act on your product.

Which MCP path do you check?

The spec isn’t final, so we check /.well-known/mcp/server-card.json, /.well-known/mcp.json and /.well-known/mcp.

Is this the same as Cloudflare’s checker?

Similar idea. Our full site audit adds SEO and AI search scores on top, with a fix for every issue.

Yes. Every tool is free with no signup.

Do you store what I enter?

Browser tools never leave your device. Live tools fetch the URL you enter and don’t save the result.

How is this different from the site audit?

This tool checks one thing in depth. The site audit checks everything at once and scores SEO, AI Search and Agent Readiness.

Tools / AI crawlers & agents

Is your site ready for AI agents?

Agents look for machine-friendly ways in before they scrape HTML. See which of the new standards your site already supports.

Free, no signup.

Domain

Example result: vercel.com · checked 2026-09-30

Agent entry points on vercel.com

Markdown for agents	✓ served for Accept: text/markdown
MCP server card	— not found
API catalog (RFC 9727)	✓ found at /.well-known/api-catalog
OpenAPI spec	— not found
A2A agent card	— not found
Content Signals in robots.txt	✓ declared

Why it matters

Agents act for users

ChatGPT agent mode and similar tools browse, compare and buy for people. They prefer sites they can read and call directly.

Markdown saves tokens

Cloudflare and Vercel serve markdown to agents that ask for it. It’s the cheapest agent upgrade to ship.

Early is cheap

Fewer than 15 sites had an MCP server card or API catalog in Cloudflare’s 2026 scan. Anything you add puts you ahead.

What it checks

Markdown for agents

Whether you answer Accept: text/markdown, or publish /index.md.

MCP server card

An MCP manifest under /.well-known, so agents can find your tools.

API catalog

RFC 9727 /.well-known/api-catalog, plus /openapi.json.

A2A agent card

/.well-known/agent-card.json for agent-to-agent protocols.

Commerce and signed agents

UCP for agent checkout, and Web Bot Auth keys for verifying signed agents.

Content Signals

The search=, ai-input= and ai-train= preferences in robots.txt.

How it works

Enter a URL

A domain or page address. No install, nothing to add to your site.

We fetch it live

Our servers request the page read-only, the way a crawler would.

Read and fix

Get the results in seconds, with what each one means.

Questions

More in AI crawlers & agents

AI Bot Access CheckerTest robots.txt and a live request for GPTBot, ClaudeBot, PerplexityBot and the agent user-agents. Catches firewall blocks.AI Crawler ViewSee the text an AI crawler gets without running JavaScript, and whether your page is an empty shell.llms.txt CheckerFetch and validate /llms.txt and /llms-full.txt against the llmstxt.org format.

Check everything at once

The site audit checks your whole site and scores SEO, AI Search and Agent Readiness in about 30 seconds.

Audit my site