PageSpeed MCP Server

Name: PageSpeed MCP Server
Author: PhialsBasement

@PhialsBasement

Repository

About PageSpeed MCP Server

Pull pagespeed data using this MCP server.

Basic information

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "Pagespeed-MCP-Server": {
      "command": "npx",
      "args": [
        "-y",
        "@smithery/cli",
        "install",
        "mcp-pagespeed-server",
        "--client",
        "claude"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is PageSpeed MCP Server?

A Model Context Protocol (MCP) server that extends AI assistant capabilities with PageSpeed Insights functionality, acting as a bridge between AI models and Google's PageSpeed Insights API for detailed website performance analysis.

How to use PageSpeed MCP Server?

Install via npm (npm install pagespeed-mcp-server) or Smithery, then configure in your AI assistant's configuration file with a GOOGLE_API_KEY and the path to the server binary. The server can be invoked with a URL and optional parameters such as strategy (mobile/desktop) and categories.

Key features of PageSpeed MCP Server

Analyzes Core Web Vitals: FCP, LCP, TTI, TBT, CLS, Speed Index, TTFB
Assesses best practices: HTTPS, JavaScript errors, deprecated APIs
Performs SEO audits: meta descriptions, robots.txt, structured data
Runs accessibility checks: ARIA validation, color contrast, heading hierarchy
Provides resource optimization suggestions: image optimization, caching, minification

Use cases of PageSpeed MCP Server

Integrate real-time PageSpeed audits into AI-powered developer assistants
Automate performance regression checks in CI/CD pipelines
Enable AI chatbots to answer website speed and SEO questions
Quickly audit accessibility and best practices for multiple URLs

FAQ from PageSpeed MCP Server

What PageSpeed metrics does the server analyze?

It provides First Contentful Paint (FCP), Largest Contentful Paint (LCP), Time to Interactive (TTI), Total Blocking Time (TBT), Cumulative Layout Shift (CLS), Speed Index, and Time to First Byte (TTFB).

How do I set up the server with Claude?

Add a JSON entry to Claude's configuration with "command": "node", "args": ["path/to/mcp-pagespeed-server/dist/index.js"], and an env field containing your GOOGLE_API_KEY.

What strategies are supported for analysis?

You can specify "strategy": "mobile" or "strategy": "desktop" in the request.

How does the server handle API rate limiting?

The README recommends using an API key to obtain higher rate limits; common troubleshooting includes checking internet connectivity and adjusting Node.js memory limits.