Puppeteer Linux

🚀 MCP-Puppeteer-Linux

A Model Context Protocol (MCP) server that provides browser automation capabilities using Puppeteer and fully supports 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

This MCP server allows LLMs to perform browser automation tasks in a Linux environment, supporting both X11 and Wayland display servers.

✨ Features

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 a web 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): CSS selector of the element to click
• puppeteer_hover
  • Hover the mouse over an element on the page.
  • Input: selector (string): CSS selector of the element to hover over
• puppeteer_fill
  • Fill in form fields.
  • Input:
    • selector (string): CSS selector of the input field
    • value (string): Value to fill in
• puppeteer_select
  • Select an element with the SELECT tag.
  • Input:
    • selector (string): CSS selector of the element to select
• puppeteer_execute_javascript
  • Execute a JavaScript expression in the target context.
  • Input:
    • expression (string): JavaScript expression to execute

Resources

• Console Log: Provides console log output, accessible using a specific URL format.
• Screenshot: Provides screenshot resources, accessible using a specific URL format.

Key Features

• Browser automation capabilities
• Display server support (X11 and Wayland)
• Dynamic environment variable configuration
• Fallback mechanism and robust error handling
• XWayland compatibility

📦 Installation

Automatic Installation via Smithery

# Automatically install using the following command:
smithery install @PhialsBasement/mcp-puppeteer-linux

Manual Installation

1. Clone this repository:

   git clone https://github.com/PhialsBasement/mcp-puppeteer_linux.git
   cd mcp-puppeteer_linux
   

2. Install dependencies and run:

   npm install
   node index.js
   

🔧 Technical Details

Wayland Support

• Automatically detect and configure Wayland environment variables.
• Support XWayland compatibility.

X11 Support

• Configure X11 environment variables to support traditional Linux display servers.

📚 Documentation

Configuration

Here is an example configuration for Claude Desktop:

{
  "mcp": {
    "servers": [
      {
        "name": "puppeteer_navigate",
        "command": "cd /path/to/app && npm start"
      },
      {
        "name": "puppeteer_screenshot",
        "command": "cd /path/to/app && npm run screenshot"
      }
    ]
  }
}

📄 License

This project is licensed under the MIT License. For more details, please refer to the LICENSE file.