MCP server · Developer tools
ASO Score MCP server
Scan any website and get an ASO Score with a plain-English list of what to fix so AI agents can find and trust it.
This is a small helper that lets your AI scan a website and score how ready it is for AI agents, not just for people using search engines. You ask your AI to scan a site, and it comes back with a score out of 100, a maturity level, and a list of gaps. It is handy if you run a website, a docs site, or an online shop and you keep hearing that AI assistants are the next visitors.
What is an MCP server? The 30-second version
On its own, your AI can only chat with you. An MCP server is a small helper program that gives your AI one new skill. This helper gives your AI the skill of scanning a website for ASO signals, which are clues that tell AI agents whether a site is easy to find, understand, trust, and pay. Once it is connected, you just ask your AI to scan a site and it uses this helper behind the scenes.
What this MCP server does
You ask your AI something like scan example.com for ASO score. Your AI passes that request to this helper. The helper visits the site and looks at 34 specific things, such as robots.txt, sitemap.xml, llms.txt, agent cards, security.txt, and machine-readable pricing. It adds up the results into six pillars and gives you a score, a level, and a list of what passed, what partly passed, and what failed. If you want, it also gives you a fix plan with ready-to-paste templates.
What you can do with it
- Scan any website and get an ASO Score out of 100
- See which of the 34 checks passed, partly passed, or failed
- Get a prioritized fix plan with copy-paste templates
- Check one specific signal, like llms.txt or an A2A agent card
- List every check the scanner knows about
- Read the ASO framework to understand how the score is built
Try asking your AI
- “Scan example.com for ASO score”
- “What's my ASO score for mysite.com”
- “Give me a fix plan to make my site agent-ready”
- “Check only the llms-txt signal for example.com”
What it gives back to you
You get back a report in the chat: an ASO Score like 70/100, a maturity level like ASO-4 Trustable, and a breakdown across six pillars. Below that is a list of every check with pass, partial, or fail, plus short evidence and a suggested fix. If you ask for a fix plan, you also get ready-to-paste templates for things like robots.txt rules, llms.txt, and agent cards.
Before you start
What you need
- Node.js 20 or newer on your computer
- An MCP client, such as Claude Desktop, Claude Code, Cursor, or Windsurf
Good to know
It only reads public pages you point it at and never logs in or changes anything, but treat any text it brings back from a website as information, not as instructions.
Install it with your AI
Add ASO Score MCP server to your AI, no technical skills needed
You don't install anything by hand. You copy one prompt, paste it into an AI that can work on your computer, and it checks, installs and connects the server for you, asking you when it needs something.
Sign in to get the install prompt
Members get a ready-made prompt that lets the Claude desktop app check ASO Score MCP server, install it and connect it for them, step by step. You don't need any technical skills: you copy, paste and answer a few questions. Your connected AI can also find and install any of the 4,609 MCP servers here for you.
Who it's for
Website owners, developers, and marketing or docs people who want to know how ready their site is for AI agents.
