Playwright Lighthouse MCP

🚀 Playwright-Lighthouse MCP Server

A MCP server that utilizes Playwright and Lighthouse to analyze website performance. Through the Model Context Protocol (MCP), LLMs can conduct website performance analysis.

🚀 Quick Start

This is a MCP server that uses Playwright and Lighthouse for website performance analysis. With the Model Context Protocol (MCP), LLMs can perform such analysis.

✨ Features

• Conduct performance analysis using Lighthouse.
• Capture screenshots of web pages.

📦 Installation

Prerequisites

• Node.js 18 or higher
• npm

Installation Steps

# Clone the repository
git clone https://github.com/kbyk004/playwright-lighthouse-mcp.git
cd playwright-lighthouse-mcp

# Install dependencies
npm install
npx playwright install

# Build
npm run build

💻 Usage Examples

Debugging MCP Server

npm run inspector

Integration with MCP Clients

This server is intended to be used with clients supporting the Model Context Protocol (MCP). For instance, it can be integrated with Claude for Desktop.

Configuration Example for Claude for Desktop

Add the following to the Claude for Desktop configuration file (~/Library/Application Support/Claude/claude_desktop_config.json):

{
  "mcpServers": {
    "playwright-lighthouse": {
      "command": "node",
      "args": [
        "/path-to/playwright-lighthouse-mcp/build/index.js"
      ]
    }
  }
}

Available Tools

1. run-lighthouse

Performs a Lighthouse performance analysis on the currently open page.

Parameters:

• url: The URL of the website to be analyzed.
• categories: An array of categories to analyze (default: ["performance"]).
  • Available categories: "performance", "accessibility", "best-practices", "seo", "pwa".
• maxItems: The maximum number of improvement items to display for each category (default: 3, max: 5).

2. take-screenshot

Captures a screenshot of the currently open page.

Parameters:

• url: The URL of the website to capture.
• fullPage: If true, captures a screenshot of the entire page (default: false).

Output Format

The analysis results consist of:

• Overall scores for each selected category with color indicators.
• Key improvement areas grouped by category.
• The path to the saved report file.

📄 License

This project is under the MIT License. See LICENSE for detailed information.