MCP server · Analytics
Google CrUX MCP server
by A1-x-Tech
Check how fast a public website really feels to visitors, on phones and computers.
This is a small helper that lets your AI look up real speed data for public websites, collected from actual Chrome users. You can ask whether a page feels fast or slow, compare phones with computers, and see how things changed over the past weeks. It is handy if you work on a website and want quick answers without opening a separate tool.
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 a new skill or a connection to an app or service. This one connects your AI to Google's Chrome UX Report, a public dataset about how real people experience websites. Once it is connected, you can ask questions in plain words and the AI goes and fetches the numbers for you.
What this MCP server does
You ask your AI something like whether a page passes Core Web Vitals on mobile. The AI sends that question to this helper. The helper talks to Google's Chrome UX Report and pulls the real-user numbers for that page or site. Then the AI explains the results in the chat, with the ratings and the overall pass or fail. Everything is read-only, so nothing on your site or in Google is changed.
What you can do with it
- Check whether a public page or site passes Core Web Vitals
- Compare how a page performs on mobile versus desktop
- Compare a single page against the whole site average
- See how LCP, INP and CLS changed over the last 25 weeks
- Look at the raw numbers and histograms for a technical review
- Ask which device groups have enough data and which do not
Try asking your AI
- “Does https://example.com pass Core Web Vitals on mobile?”
- “Compare this page with the site average and show how mobile differs from desktop.”
- “How did LCP, INP and CLS change for example.com over the last 25 weeks?”
- “Show me the raw CrUX numbers for https://example.com/pricing.”
What it gives back to you
You get back a short written answer in the chat, with the key numbers (LCP, INP, CLS), their good, needs-improvement or poor rating, and an overall pass or fail. For comparisons you also see the different device groups and how much traffic each one has. Trend questions come back as a week-by-week view. If Google has no data for that page, you simply get told there is no data, which is a normal answer.
Before you start
What you need
- Node.js 20 or newer installed on your computer
- A Google Cloud API key with the Chrome UX Report API turned on (a kind of password for apps; Google gives you one for free, no billing account needed)
Good to know
It only reads public Google data, so it cannot change your site or rankings, but it does need your Google Cloud API key, so keep that key private and treat it like a password.
Install it with your AI
Add Google CrUX 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 Google CrUX 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
People who look after a website, like marketers, content editors, SEO folks and product managers, who want quick speed answers without opening a separate tool.
