- Home
- MCP Integrations
- Google PageSpeed MCP Server
Google PageSpeed MCP Server
Connect to the Google PageSpeed MCP server to analyze webpage performance, pull Core Web Vitals, and get Lighthouse audit results using AI agents on Gumloop, Claude, or Cursor.
Try Google PageSpeed now
Type what you want done. Sign in and run it live with an AI agent.

Installation
Get StartedCreate a Gumloop Account
To use this MCP, you need a Gumloop account. If you don't have one yet, you can create one for free.
Copy Your Server URL
Copy your MCP server URL and add it to your client. You'll be prompted to authorize on first use.
Tools (3)
Run Pagespeed Analysis
5 creditsRun PageSpeed analysis on a URL and get Lighthouse scores and loading experience
Get Lighthouse Audits
5 creditsGet Lighthouse audit results for a specific category on a URL
Get Core Web Vitals
5 creditsGet Core Web Vitals (LCP, FID, CLS, INP, TTFB) field data for a URL
What is Google PageSpeed MCP?
The Google PageSpeed MCP server gives AI agents access to Google PageSpeed Insights. That means agents can run a full PageSpeed analysis on any URL, pull Core Web Vitals field data, and get Lighthouse audit results by category. An AI agent can measure and explain web performance for any page.
If you spend time running PageSpeed Insights by hand, copying scores into a spreadsheet, or checking pages one at a time after a release, an AI agent can take over a lot of that work. Describe what you need, and your AI agent will run the analysis and surface the numbers for you.
MCP stands for Model Context Protocol. It’s an open standard that gives AI agents a way to connect to external tools and services. Instead of getting a PageSpeed Insights API key, writing code against the API, and parsing the Lighthouse JSON yourself, you connect the Google PageSpeed MCP server on Gumloop. After that, you analyze pages just by asking your AI agent in plain language.
Related MCP servers
Google Search Console MCP Server
Query Search Console performance, indexing, properties, and sitemap data
Google Analytics MCP Server
Run reports, manage accounts and properties, configure custom dimensions, metrics and conversions, and send server-side events on Google Analytics.
Semrush MCP Server
Access Semrush SEO and digital marketing analytics data
Ahrefs MCP Server
Access Ahrefs SEO and backlink analytics data
Google Sheets MCP Server
Read, write and update your Google Sheets
Slack MCP Server
Interact with Slack channels and messages
What you can do with Google PageSpeed MCP on Gumloop
Run a full PageSpeed analysis
Analyze any URL and get its Lighthouse scores along with real-world loading experience. A complete performance snapshot for a page in a single call.
Pull Core Web Vitals
Get field data for the Core Web Vitals — LCP, INP, and CLS — plus TTFB for a URL, so an agent can report on the metrics Google actually uses to judge page experience.
Get Lighthouse audits by category
Retrieve detailed Lighthouse audit results for a specific category, like performance, accessibility, SEO, or best practices, so an agent can explain exactly what’s slowing a page down and what to fix.
How to connect the Gumloop Google PageSpeed MCP Server
- 1
Create a free Gumloop account
Sign up at gumloop.com. No credit card required.
- 2
Add the Google PageSpeed MCP server
Copy your MCP server URL from Gumloop and add it to your preferred client (Claude, Cursor, or Gumloop workflows). You'll authorize on first use.
- 3
Start using Google PageSpeed in your AI workflows
That's it. Your AI agent can now analyze webpage performance, pull Core Web Vitals, and get Lighthouse audits for any URL. Use it inside a Gumloop automation, in Claude Desktop, or in Cursor.
Google PageSpeed MCP use cases
Automated performance monitoring
An AI agent can run a PageSpeed analysis on your key pages on a schedule, track the scores and Core Web Vitals over time, and flag a regression in Slack the moment performance drops. Surface issues before users feel them.
SEO and site audits
Have an agent run Lighthouse audits across a set of pages, pull the performance, accessibility, SEO, and best-practices results, and compile a prioritized list of what to fix. Get a full audit without having to click through PageSpeed Insights manually.
Competitor benchmarking
Point an agent at your URL and a few competitors’, then have it compare the Lighthouse scores and Core Web Vitals side by side. Get a quick read on where you stand on page experience.
Pre-launch and post-release checks
Before a launch or right after a deploy, an agent can analyze the affected pages and flag any score or Core Web Vitals regression, so performance problems get caught at release instead of in production.
Cross-platform performance reporting
Combine PageSpeed with Google Sheets and Slack in a single AI agent: run analyses on a schedule, log the scores to a sheet to build a trend line, and post a weekly performance summary to your team.
Why use Gumloop for Google PageSpeed MCP
Built-in connection, no API key
Building your own PageSpeed MCP server means managing a PageSpeed Insights API key, handling the API, and parsing dense Lighthouse JSON. Gumloop comes with the PageSpeed connection built in, so you can start analyzing pages right away. No API key and no code.
Works with multiple MCP clients
Use the Google PageSpeed MCP server endpoint in Claude Desktop, Cursor, or directly inside Gumloop. Same server URL, works with any MCP client.
Chain PageSpeed with 100+ other integrations
Combine PageSpeed with Google Sheets, Slack, and other MCP tools in a single AI agent. Run an analysis, summarize it with an LLM, and write the scores wherever your team tracks them.
Enterprise-grade and scalable
Built for teams, with role-based permissions and dedicated support for Pro users. Analyze pages at volume as part of your monitoring and reporting workflows.
Pricing includes a free plan
You can test the Google PageSpeed MCP integration on Gumloop’s free tier before committing. Paid plans start at $37/month.
Frequently asked questions
Ship Google PageSpeed agents in minutes
Connect any AI agent to 100+ MCP servers, zero setup.