About

Browser MCP Experimental extends the original Browser MCP with JavaScript execution capabilities. This experimental fork allows you to run arbitrary JavaScript code in the browser context through AI applications like VS Code, Claude, Cursor, and Windsurf.

🚀 New in Experimental

JavaScript Execution Tool

Tool: browser_execute_javascript
Description: Execute JavaScript code in the browser context and get results back.

Examples:

// Get page information
document.title

// Query DOM elements  
document.querySelectorAll('button').length

// Access browser APIs
localStorage.getItem('username')

// Complex operations
JSON.stringify({
  url: window.location.href,
  title: document.title,  
  links: Array.from(document.querySelectorAll('a')).map(a => ({
    text: a.textContent,
    href: a.href
  }))
})

Installation

npm install @browsermcp/mcp-experimental@experimental

Features

• ⚡ Fast: Automation happens locally on your machine, resulting in better performance without network latency.
• 🔒 Private: Since automation happens locally, your browser activity stays on your device and isn't sent to remote servers.
• 👤 Logged In: Uses your existing browser profile, keeping you logged into all your services.
• 🥷🏼 Stealth: Avoids basic bot detection and CAPTCHAs by using your real browser fingerprint.

Contributing

This repo contains all the core MCP code for Browser MCP, but currently cannot yet be built on its own due to dependencies on utils and types from the monorepo where it's developed.

Credits

Browser MCP was adapted from the Playwright MCP server in order to automate the user's browser rather than creating new browser instances. This allows using the user's existing browser profile to use logged-in sessions and avoid bot detection mechanisms that commonly block automated browser use.