Connect Bot Appétit to your AI tool

The address

Every client asks for the same thing: the server address. It is Streamable HTTP. Nothing to sign in to for the page tools; the account tools ask for your approval the first time you use one.

https://bot-appetit-beta.milkmoonworkers.workers.dev/mcp

What it can do

• scan_page Check one web page for AEO, SEO and performance: can a machine consume it?
• get_report Get a stored Bot Appétit report by scan id, the same report a person sees at botappetit.ai/r/<id>.
• page_history List every stored Bot Appétit scan of one exact page, newest first, with the score at the time and how it moved since the scan before.
• list_checks List every check Bot Appétit runs on a page, grouped by category, with the id of each.
• explain_check Explain one Bot Appétit check: what it looks at, why it matters for machines reading a page, and what good looks like.
• request_site_scan A whole-site scan reads a representative sample of a site and needs a person with a Bot Appétit account, and an agent never creates one.
• leaderboard The highest-scoring sites by category, from the latest Bot Appétit scan of each site's homepage: rank, host, score out of 100, grade and a link to the full report.

Every answer comes with the link to the full report on botappetit.ai, so you can open it and share it.

With your own account

These work on your account, so they need your approval. The first time your AI tool uses one, it opens a page in your browser. You sign in, or create a free account and verify your email address there, then allow the connection. You do this yourself: an AI tool never creates an account for anyone. You can remove the connection in your tool at any time.

• start_site_scan Start a whole-site scan for the signed-in person's account: Bot Appétit reads a representative sample of the site (not every page) and scores it.
• site_scan_status Read one of the signed-in person's site scans: whether it is still running, and once it has finished the score, the checks that failed, the category scores and the pages it covered, each page with a link to its own full report.
• list_sites List the sites the signed-in person follows in Bot Appétit, newest activity first, each with its latest site-scan score, the change since the scan before, and the trend.
• site_history Read one of the signed-in person's sites over time: every site scan of it newest first with the score and the change since the previous scored scan (a change across a scoring update or different pinned pages is marked, not passed off as the site's own), the pinned pages, and the monthly re-scan settings.
• set_pins Pin or unpin pages on one of the signed-in person's sites.
• set_rescan_settings Turn the signed-in person's monthly re-scans of their sites on or off, and the email of each result on or off.
• share_site_scan Create or stop the unlisted share link for one of the signed-in person's site scans.

A site scan is private to your account until you choose to share it.

Set it up in your tool

claude mcp add --transport http bot-appetit https://bot-appetit-beta.milkmoonworkers.workers.dev/mcp

{
  "mcpServers": {
    "bot-appetit": {
      "url": "https://bot-appetit-beta.milkmoonworkers.workers.dev/mcp"
    }
  }
}

Limits

Reading a stored report is generous. Starting a new scan has a stricter limit, because each one fetches a real page. Without an account, one connection can also start at most 50 new scans a day (the count resets at midnight UTC); stored results never count against it. Connecting your account raises the limits and lifts the daily cap. If you go over, the answer says how long to wait. Wait, then ask again.

Where it is listed

• Listed on mcpservers.org ↗ (opens in a new tab), Glama ↗ (opens in a new tab) and the official MCP Registry ↗ (opens in a new tab).
• Coming soon to Claude and ChatGPT — now in review.

More for agents

• The same tools as a REST API
• Skills your agent can install
• llms.txt

Want your own site checked? Scan a page →, or ask your AI tool to do it once it is connected.