PageSpeed

PageSpeed MCP Server extends AI assistants with Google's PageSpeed Insights capabilities, enabling you to perform detailed web performance analyses for any URL and incorporate those insights into automated workflows.

How to use

You use the PageSpeed MCP Server by running a local (stdio) MCP endpoint and connecting your MCP client to it. The server analyzes a target URL via PageSpeed Insights and returns structured results that cover performance metrics, best practices, SEO signals, and accessibility signals. You can request analyses for mobile or desktop viewpoints and tailor the scope with categories and locale settings. Use the results to inform optimization steps, compare pages, or automate performance checks as part of your assistant’s responses.

How to install

Prerequisites you need before installing:
- Node.js installed on your machine (version compatible with the MCP server build).
- npm (comes with Node.js) and optionally npx for quick CLI operations.

Option A: Install via Smithery (recommended for automatic setup with a client)

npx -y @smithery/cli install mcp-pagespeed-server --client claude

Option B: Manual installation (local MSP server package)

npm install pagespeed-mcp-server

Next, configure your client to connect to the PageSpeed MCP Server. Use the provided configuration block to pass the server command, arguments, and your Google API key. The server runs locally and returns results to the client during questions about a URL.

Configuration and usage notes

Configure the PageSpeed MCP in your client’s settings to point to the local server process. The standard setup uses a Node process launching the MCP server from its built file path.

{
  "pagespeed": {
    "command": "node",
    "args": ["path/to/mcp-pagespeed-server/dist/index.js"],
    "env": {
       "GOOGLE_API_KEY": "<YOUR-API-KEY>"
    }
  }
}

Advanced usage and options

You can customize the analysis by selecting which categories to include, choosing the strategy (mobile or desktop), and setting the locale. The server supports performance, accessibility, best-practices, and SEO analyses, and returns a structured JSON payload with detailed audits and timing data.

{
  "strategy": "mobile",
  "categories": ["performance", "accessibility", "best-practices", "seo"],
  "locale": "en",
  "threshold": {
    "performance": 90,
    "accessibility": 100,
    "best-practices": 90,
    "seo": 90
  }
}

Available tools

analyze

Performs a PageSpeed Insights analysis for a given URL and returns results across performance, accessibility, best-practices, and SEO categories.