Puppeteer Real Browser MCP Server
@withLinda
About Puppeteer Real Browser MCP Server
Provides AI assistants with powerful, detection-resistant browser automation capabilities built on ZFC Digital's puppeteer-real-browser package.
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"puppeteer-real-browser": {
"command": "npx",
"args": [
"puppeteer-real-browser-mcp-server@latest"
]
}
}
}Tools
11Initialize a new browser instance with anti-detection features and automatic Chrome path detection
Navigate to a URL
**Recommended** method to get page content (HTML or text) - More reliable than screenshots for content analysis and navigation tasks
Click on an element
Type text into an input field
Wait for various conditions
Close the browser instance
Attempt to solve CAPTCHAs (if supported)
Perform random scrolling with natural timing
Find CSS selector for element containing specific text
Extract page content and save it as a formatted markdown file
Overview
What is Puppeteer Real Browser MCP Server?
It is an MCP (Model Context Protocol) server that provides AI assistants with detection-resistant browser automation capabilities, built on the puppeteer-real-browser package. It acts as a bridge between AI assistants and a real browser, enabling stealth browsing that bypasses common bot detection mechanisms.
How to use Puppeteer Real Browser MCP Server?
No installation is required for end users – use npx puppeteer-real-browser-mcp-server@latest in your AI assistant's configuration. For Claude Desktop, add the server to claude_desktop_config.json. For Claude Code CLI, run claude mcp add puppeteer-real-browser -- npx puppeteer-real-browser-mcp-server@latest. For Cursor IDE, configure via .cursor/mcp.json. Developers can install globally or clone the repo for contributions.
Features of Puppeteer Real Browser MCP Server
- Stealth by default with anti-detection features
- Smart Chrome detection across 15+ installation paths (Windows)
- Dynamic selector discovery without hardcoded selectors
- Proxy support and captcha handling (reCAPTCHA, hCaptcha, Turnstile)
- 11 tools covering all browser automation needs
- Robust error handling with circuit breaker pattern and timeout controls
Use cases of Puppeteer Real Browser MCP Server
- Browse websites and search for products (e.g., "Go to amazon.com and search for laptops")
- Fill out and submit web forms automatically
- Extract structured data like prices, product listings, or page content
- Automate login and invoice download workflows
- Solve captchas during automated browsing sessions
FAQ from Puppeteer Real Browser MCP Server
Do I need to install this package to use it?
No. The npx command automatically downloads and runs the latest version without permanent installation. Only developers contributing to the project need to install.
What are the prerequisites?
Node.js 18 or higher and Google Chrome/Chromium installed. Platform-specific paths are automatically detected on Windows, macOS, and Linux.
How do I configure the server with Claude Desktop?
Add a JSON entry to claude_desktop_config.json (located at %APPDATA%\Claude\ on Windows, ~/Library/Application Support/Claude/ on Mac, or ~/.config/Claude/ on Linux) with the command npx and args ["puppeteer-real-browser-mcp-server@latest"].
Can I use a proxy or custom Chrome path?
Yes. Use environment variables such as CHROME_PATH and PROXY_URL when starting the server, for example via the Claude Code CLI -e flag or in the JSON configuration.
Is this project stable?
The project is under active development and marked as "UNDER MAINTENANCE". Some features may be incomplete or change without notice.
Frequently asked questions
Do I need to install this package to use it?
No. The `npx` command automatically downloads and runs the latest version without permanent installation. Only developers contributing to the project need to install.
What are the prerequisites?
Node.js 18 or higher and Google Chrome/Chromium installed. Platform-specific paths are automatically detected on Windows, macOS, and Linux.
How do I configure the server with Claude Desktop?
Add a JSON entry to `claude_desktop_config.json` (located at `%APPDATA%\Claude\` on Windows, `~/Library/Application Support/Claude/` on Mac, or `~/.config/Claude/` on Linux) with the command `npx` and args `["puppeteer-real-browser-mcp-server@latest"]`.
Can I use a proxy or custom Chrome path?
Yes. Use environment variables such as `CHROME_PATH` and `PROXY_URL` when starting the server, for example via the Claude Code CLI `-e` flag or in the JSON configuration.
Is this project stable?
The project is under active development and marked as "UNDER MAINTENANCE". Some features may be incomplete or change without notice.
Basic information
More Browser Automation MCP servers
Umut Naci
firecrawlThe API to search, scrape, and interact with the web at scale. 🔥
BrowserTools MCP
AgentDeskAIMonitor browser logs directly from Cursor and other MCP compatible IDEs.
Apify Model Context Protocol (MCP) Server
apifyThe Apify MCP server enables your AI agents to extract data from social media, search engines, maps, e-commerce sites, or any other website using thousands of ready-made scrapers, crawlers, and automation tools available on the Apify Store.
browser-mcp
djydeA browser extension and MCP server that allows you to interact with the browser you are using.
Fetch MCP Server
zcaceresA flexible HTTP fetching Model Context Protocol server.
Comments