MCP Puppeteer Linux

🚀 MCP-Puppeteer-Linux

A Model Context Protocol server that provides browser automation capabilities using Puppeteer, fully supporting Linux display servers (X11 and Wayland). This server enables LLMs to interact with web pages, take screenshots, and execute JavaScript in a real browser environment.

🚀 Quick Start

To get started with MCP-Puppeteer-Linux, follow these steps:

1. First, install the dependencies:

npm install puppeteer

2. Create a configuration file and start the service.

✨ Features

• Browser automation with Linux display server support
• Automatic detection and configuration of X11/Wayland
• Console log monitoring
• Screenshot capabilities
• JavaScript execution
• Basic web page interactions (navigation, clicking, filling forms)

📦 Installation

Install Dependencies

npm install puppeteer

💻 Usage Examples

Claude Desktop Configuration

{
  "mcpServers": {
    "puppeteer": {
      "command": "npx",
      "args": ["ts-node", "/path/to/your/script.ts"]
    }
  }
}

📚 Documentation

Display Server Support

This branch adds automatic detection and configuration for Linux display servers:

• Automatic detection of X11/Wayland
• Dynamic environment variable configuration
• Support for various desktop environments (GNOME, KDE, etc.)
• Fallback mechanism and robust error handling
• XWayland compatibility

Components

Tools

• puppeteer_navigate
  • Navigate to any URL in the browser
  • Input: url (string)
• puppeteer_screenshot
  • Take a screenshot of the page or a specific element
  • Input:
    • name (string, required): Screenshot name
    • selector (string, optional): CSS selector for the element to capture
    • width (number, optional, default: 800): Screenshot width
    • height (number, optional, default: 600): Screenshot height
• puppeteer_click
  • Click on an element on the page
  • Input: selector (string): Selector of the element to click
• puppeteer_hover
  • Hover the mouse over an element on the page
  • Input: selector (string): Selector of the element to hover over
• puppeteer_fill
  • Fill an input field
  • Input:
    • selector (string): Selector of the input field
    • value (string): Value to fill
• puppeteer_select
  • Select an element with a SELECT tag
  • Input:
    • selector (string): Selector of the element to select
    • value (string): Value to select
• puppeteer_evaluate
  • Execute JavaScript in the browser console
  • Input: script (string): JavaScript code to execute

Resources

The server provides access to two types of resources:

1. Console Logs (console://logs)
   • Text format of the browser console output
   • Includes all console messages in the browser
2. Screenshots (screenshot://<name>)
   • PNG images of screenshots specified by name
   • Access captured screens by screenshot name

Display Server Support

• Wayland: Automatically detects and uses the Wayland display server.
• X11: Automatically detects and uses the X11 display server.

With the above settings, you can flexibly run Puppeteer in different display environments.

🔧 Technical Details

Claude Desktop Configuration

{
  "mcpServers": {
    "puppeteer": {
      "command": "npx",
      "args": ["ts-node", "/path/to/your/script.ts"]
    }
  }
}