mcpField
@
@enemyrr/mcp-server-pagespeed

@enemyrr/mcp-server-pagespeed

Local
github.com/enemyrrDeveloper Tools11Updated 89w ago
Repository

About @enemyrr/mcp-server-pagespeed

@enemyrr/mcp-server-pagespeed is an MCP server that lets AI models analyze webpage performance using Google PageSpeed Insights. Its analysis includes loading metrics and prioritized improvement suggestions.

Key features

  1. 01Analyze webpages with Google PageSpeed Insights
  2. 02Return performance scores and loading metrics
  3. 03Provide prioritized improvement suggestions
  4. 04Handle URL and API errors

Use cases

  1. 01Review a webpage's performance
  2. 02Inspect loading experience metrics
  3. 03Identify prioritized performance improvements

MCP support

Exposes an analyze_pagespeed tool to MCP clients, accepting a webpage URL and returning PageSpeed Insights analysis.

#mcp-server#pagespeed#performance-analysis

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "pagespeed": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-server-pagespeed"
      ]
    }
  }
}
Run commandnpx -y mcp-server-pagespeed

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmmcp-server-pagespeed

Tools

1

Saved tool list · updated 3w ago

ParameterTypeRequiredDescription
urlstringYesThe URL to analyze

Details

From the project README

@enemyrr/mcp-server-pagespeed

A Model Context Protocol server that provides Google PageSpeed Insights analysis. This server enables AI models to analyze webpage performance through a standardized interface.

Server Pagespeed MCP server

Installation & Setup for Cursor IDE

  1. Clone and build the project:
git clone https://github.com/enemyrr/mcp-server-pagespeed.git
cd mcp-server-pagespeed
npm install
npm run build
  1. Add the server in Cursor IDE settings:
    • Open Command Palette (Cmd/Ctrl + Shift + P)
    • Search for "MCP: Add Server"
    • Fill in the fields:
      • Name: pagespeed
      • Type: command
      • Command: node /absolute/path/to/mcp-server-pagespeed/build/index.js

Note: Replace /absolute/path/to/ with the actual path where you cloned and built the project.

Command-line Usage

Just run:

npx mcp-server-pagespeed

Available Tools

analyze_pagespeed

Analyze a webpage using Google PageSpeed Insights API.

use_mcp_tool({
  server_name: "pagespeed",
  tool_name: "analyze_pagespeed",
  arguments: {
    url: "https://example.com"
  }
});

The tool returns:

  • Overall performance score (0-100)
  • Loading experience metrics
    • First Contentful Paint
    • First Input Delay
  • Top 5 improvement suggestions with:
    • Title
    • Description
    • Potential impact
    • Current value

Features

  • Real-time webpage performance analysis
  • Detailed loading experience metrics
  • Prioritized improvement suggestions
  • Comprehensive error handling
  • TypeScript support

Error Handling

The server provides detailed error messages for:

  • Invalid URLs
  • API request failures
  • Connection issues
  • Invalid tool calls

Contributing

Contributions are welcome! Please feel free to submit a Pull Request to https://github.com/enemyrr/mcp-server-pagespeed

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.