Chrome MCP Server - AI Browser Control

Turn Chrome into an MCP server. Let AI control your browser - navigate, click, fill forms, take screenshots.

Chrome MCP Server — AI-Powered Browser Automation via Model Context Protocol The best MCP server for Chrome browser automation. Transform your Chrome browser into a fully-featured MCP (Model Context Protocol) server, enabling AI coding assistants to interact with your browser in real time. 🔧 PREREQUISITES - Node.js ≥ 20.0.0 - Chrome or Chromium browser 📦 QUICK SETUP (3 steps) 1. Install the native bridge: npm install -g mcp-chrome-bridger Then run: mcp-chrome-bridger register Or pnpm install -g mcp-chrome-bridger Then run: mcp-chrome-bridger register 2. Load this extension and click "Connect" in the popup. 3. Add to your MCP client config (Claude Code / Cursor / Windsurf / Kiro / Cline etc), following the connection info shown in the popup: { "mcpServers": { "mcp-chrome": { "type": "http", "url": "http://127.0.0.1:12306/mcp" } } } ✨ KEY FEATURES - Navigate and control browser tabs programmatically - Take full-page or viewport screenshots - Extract and parse page content (text, HTML, DOM) - Interact with page elements — click, scroll, hover - Fill and submit forms automatically - Capture and inspect network requests - Search browsing history and bookmarks - Multi-tab management and coordination 🤖 COMPATIBLE AI CLIENTS Works with any MCP-compatible AI assistant: 🔒 PRIVACY & SECURITY This extension only communicates with a local native bridge on your own machine (127.0.0.1). No data is sent to external servers by the extension itself. 📖 OPEN SOURCE Full source code and documentation available on GitHub: https://github.com/femto/mcp-chrome ⚠️ REQUIREMENT: The mcp-chrome-bridger npm package must be installed on your system for full functionality.