MCP-Puppeteer-Linux
Automate web browsers on Linux using Puppeteer. Enables LLMs to interact with web pages, take screenshots, and execute JavaScript.
MCP-Puppeteer-Linux
A Model Context Protocol server that provides browser automation capabilities using Puppeteer, with full support for 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.
Display Server Support
This fork adds automatic detection and configuration for Linux display servers:
- Automatic X11/Wayland detection
- Dynamic environment variable configuration
- Support for various desktop environments (GNOME, KDE, etc.)
- Fallback mechanisms and robust error handling
- XWayland compatibility
Components
Tools
- puppeteer_navigate
- Navigate to any URL in the browser
- Input:
url(string)
- puppeteer_screenshot
- Capture screenshots of the entire page or specific elements
- Inputs:
name(string, required): Name for the screenshotselector(string, optional): CSS selector for element to screenshotwidth(number, optional, default: 800): Screenshot widthheight(number, optional, default: 600): Screenshot height
- puppeteer_click
- Click elements on the page
- Input:
selector(string): CSS selector for element to click
- puppeteer_hover
- Hover elements on the page
- Input:
selector(string): CSS selector for element to hover
- puppeteer_fill
- Fill out input fields
- Inputs:
selector(string): CSS selector for input fieldvalue(string): Value to fill
- puppeteer_select
- Select an element with SELECT tag
- Inputs:
selector(string): CSS selector for element to selectvalue(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:
- Console Logs (
console://logs)- Browser console output in text format
- Includes all console messages from the browser
- Screenshots (
screenshot://<name>)- PNG images of captured screenshots
- Accessible via the screenshot name specified during capture
Key Features
- Browser automation with Linux display server support
- Automatic X11/Wayland detection and configuration
- Console log monitoring
- Screenshot capabilities
- JavaScript execution
- Basic web interaction (navigation, clicking, form filling)
Configuration
Claude Desktop Configuration
{
"mcpServers": {
"puppeteer": {
"command": "npx",
"args": ["ts-node", "/path/to/index.ts"]
}
}
}
Installation
Installing via Smithery
To install Puppeteer Linux for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @PhialsBasement/mcp-puppeteer-linux --client claude
Manual Installation
- Clone the repository:
git clone https://github.com/PhialsBasement/MCP-Puppeteer-Linux.git
- Install dependencies:
npm install
- Start the server:
ts-node index.ts
Display Server Details
The server automatically detects and configures the appropriate display environment:
Wayland Support
- Detects Wayland sessions via
WAYLAND_DISPLAY - Configures necessary environment variables:
WAYLAND_DISPLAYQT_QPA_PLATFORMGDK_BACKENDMOZ_ENABLE_WAYLANDXDG_SESSION_TYPE
X11 Support
- Fallback for traditional X11 sessions
- Handles X11-specific variables:
DISPLAYXAUTHORITY
- Supports various desktop environments and window managers
License
This MCP server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.
Serveurs connexes
Bright Data
sponsorDiscover, extract, and interact with the web - one interface powering automated access across the public internet.
Crawl4AI RAG
Integrate web crawling and Retrieval-Augmented Generation (RAG) into AI agents and coding assistants.
Hacker News
Fetches and parses stories from Hacker News, providing structured data for top, new, ask, show, and job posts.
Conduit
Headless browser with SHA-256 hash-chained audit trails and Ed25519-signed proof bundles. MCP server for AI agents.
Fetch
Fetch web content as HTML, JSON, plain text, or Markdown.
transcriptor-mcp
An MCP server (stdio + HTTP/SSE) that fetches video transcripts/subtitles via yt-dlp, with pagination for large responses. Supports YouTube, Twitter/X, Instagram, TikTok, Twitch, Vimeo, Facebook, Bilibili, VK, Dailymotion. Whisper fallback — transcribes audio when subtitles are unavailable (local or OpenAI API). Works with Cursor and other MCP host
Weibo
Scrape Weibo user information, feeds, and perform searches.
Crawl4AI
Web scraping skill for Claude AI. Crawl websites, extract structured data with CSS/LLM strategies, handle dynamic JavaScript content. Built on crawl4ai with complete SDK reference, example scripts, and tests.
WebDriverIO
Automate web browsers using WebDriverIO. Supports actions like clicking, filling forms, and taking screenshots.
Skyvern
MCP Server to let Claude / your AI control the browser
Fetch as Markdown MCP Server
Fetches web pages and converts them to clean markdown, focusing on main content extraction.
