Aeo Mcp

Name: Aeo Mcp
Author: arthurcarlsonn

by arthurcarlsonncommunityv1.0.1

An MCP server that helps AI agents inspect a website’s AI visibility by checking crawler permissions, llms.txt, structured data, and on-page signals. It also runs a 29-check AI-readiness audit and returns read-only analysis for a given URL.

From the registry: AEO tools for AI agents: crawler permissions, llms.txt, structured data, AI-readiness audit.

GitHub Repository

Install & configure

Prerequisites

required
Install Node.js and npm
Node.js is required to run the server via npx.

Install in your client

Paste into the AI you're chatting with — it will figure out the rest

Please install the `aeo-mcp` MCP server into my current AI client (that's you).

Required prerequisites (do these first if not already done):
- **Install Node.js and npm** — Node.js is required to run the server via npx.

Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["-y","aeo-mcp"]

Note: The README provides the same stdio configuration for Claude Desktop and Cursor. No API keys or environment variables are required.

Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.

Note: The README provides the same stdio configuration for Claude Desktop and Cursor. No API keys or environment variables are required.

Tools (5)

audit_url

Runs a full AI-readiness audit for a URL, returning a score, grade, category breakdown, and failed/warned checks with fixes.

check_ai_crawlers

Checks robots.txt policy for major AI bots and returns per-bot allow/block verdicts, matching rules, and sitemaps.

inspect_llms_txt

Detects and validates a site’s llms.txt, returning its title, summary, sections, structural issues, and raw excerpt.

extract_structured_data

Extracts schema markup from a page, including JSON-LD types, key fields, and parse errors.

extract_page_signals

Extracts on-page signals such as title, meta description, h1, canonical, language, text ratio, heading outline, and whether the page is client-side rendered.