8000 GitHub - davincinewton/mcp-chrome-python: Chrome MCP Server is a Chrome extension-based Model Context Protocol (MCP) server that exposes your Chrome browser functionality to AI assistants like Claude, enabling complex browser automation, content analysis, and semantic search. Β· GitHub
[go: up one dir, main page]

Skip to content
< 7FFF link crossorigin="anonymous" media="all" rel="stylesheet" href="https://github.githubassets.com/assets/primer-react-brand-css.99dddccb73417aaf.module.css" />

About

Chrome MCP Server is a Chrome extension-based Model Context Protocol (MCP) server that exposes your Chrome browser functionality to AI assistants like Claude, enabling complex browser automation, content analysis, and semantic search.

Resources

Contributing

Stars

0 stars

Watchers

0 watching

Forks

Β 
Β 

Latest commit

Β 

History

213 Commits

Folders and files

NameName
Last commit message
Last commit date
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 
Β 

Repository files navigation

Chrome MCP Server πŸš€

Stars License: MIT TypeScript Chrome Extension Release

🌟 Turn your Chrome browser into your intelligent assistant - Let AI take control of your browser, transforming it into a powerful AI-controlled automation tool.

πŸ“– Documentation: English | δΈ­ζ–‡

The project is under active development. Python bridge now available - no Node.js required!


🎯 What is Chrome MCP Server?

Chrome MCP Server is a Chrome extension-based Model Context Protocol (MCP) server that exposes your Chrome browser functionality to AI assistants like Claude, enabling complex browser automation, content analysis, and semantic search. Unlike traditional browser automation tools (like Playwright), Chrome MCP Server directly uses your daily Chrome browser, leveraging existing user habits, configurations, and login states, allowing various large models or chatbots to take control of your browser and truly become your everyday assistant.

✨ New Features(2025/12/30)

  • A New Visual Editor for Claude Code & Codex, for more detail here: VisualEditor

✨ Core Features

  • 😁 Chatbot/Model Agnostic: Let any LLM or chatbot client or agent you prefer automate your browser
  • ⭐️ Use Your Original Browser: Seamlessly integrate with your existing browser environment (your configurations, login states, etc.)
  • πŸ’» Fully Local: Pure local MCP server ensuring user privacy
  • πŸš„ Streamable HTTP: Streamable HTTP connection method
  • 🏎 Cross-Tab: Cross-tab context
  • 🧠 Semantic Search: Built-in vector database for intelligent browser tab content discovery
  • πŸ” Smart Content Analysis: AI-powered text extraction and similarity matching
  • 🌐 20+ Tools: Support for screenshots, network monitoring, interactive operations, bookmark management, browsing history, and 20+ other tools
  • πŸš€ SIMD-Accelerated AI: Custom WebAssembly SIMD optimization for 4-8x faster vector operations

πŸ†š Comparison with Similar Projects

Comparison Dimension Playwright-based MCP Server Chrome Extension-based MCP Server
Resource Usage ❌ Requires launching independent browser process, installing Playwright dependencies, downloading browser binaries, etc. βœ… No need to launch independent browser process, directly utilizes user's already open Chrome browser
User Session Reuse ❌ Requires re-login βœ… Automatically uses existing login state
Browser Environment ❌ Clean environment lacks user settings βœ… Fully preserves user environment
API Access ⚠️ Limited to Playwright API βœ… Full access to Chrome native APIs
Startup Speed ❌ Requires launching browser process βœ… Only needs to activate extension
Response Speed 50-200ms inter-process communication βœ… Faster

πŸš€ Quick Start

Prerequisites

  • Node.js >= 20.0.0 and pnpm/npm
  • Chrome/Chromium browser

Installation Steps

  1. Clone the repository
git clone https://github.com/davincinewton/mcp-chrome-python.git
cd mcp-chrome-python
  1. Install the Python bridge

From the repository root:

pip install -e app/bridge-python

Or install from source without cloning:

pip install "mcp-chrome-bridge @ git+https://github.com/davincinewton/mcp-chrome-python.git#subdirectory=app/bridge-python"
  1. Build the Chrome Extension

    From the repository root:

    pnpm install
    pnpm run build:shared
    pnpm run build:extension
  2. Load Chrome Extension

    • Open Chrome and go to chrome://extensions/
    • Enable "Developer mode"
    • Click "Load unpacked" and select the app/chrome-extension folder from the cloned repository
    • Click the extension icon to open the plugin, then click connect to see the MCP configuration Screenshot 2025-06-09 15 52 06

Uninstall

pip uninstall mcp-chrome-bridge

Usage with MCP Protocol Clients

Start the Bridge Server

mcp-chrome-bridge

The server starts two services:

  • HTTP/SSE Server on port 127.0.0.1:12306 - For MCP client connections
  • WebSocket Server on port 127.0.0.1:12307 - For Chrome extension communication

Configure Your MCP Client

Add the following configuration to your MCP client:

{
  "mcpServers": {
    "chrome-mcp-server": {
      "type": "streamableHttp",
      "url": "http://127.0.0.1:12306/mcp"
    }
  }
}

That's it! The bridge automatically handles communication between your MCP client and the Chrome extension.

πŸ› οΈ Available Tools

Complete tool list: Complete Tool List

πŸ“Š Browser Management (4 tools)
  • get_windows_and_tabs - List all browser windows and tabs
  • chrome_navigate - Navigate to URLs, refresh, or go back/forward
  • chrome_switch_tab - Switch the current active tab
  • chrome_close_tabs - Close specific tabs
πŸ”Ž Search (2 tools)
  • chrome_search - Multi-engine web search in the browser (DDG/Bing/Google/Brave/Mojeek/Ecosia/Baidu/auto); returns title/url/snippet, visible tab auto-closed
  • chrome_google_search - Deep Google search: resolves real URLs + captures article full text + key image URLs for the top-N results
πŸ“Έ Screenshots & Visual (2 tools)
  • chrome_screenshot - Screenshot with element targeting, full-page, custom dimensions
  • chrome_gif_recorder - Record tab activity as an animated GIF
🌐 Network (2 tools)
  • chrome_network_capture - Unified capture (action:'start'|'stop'; optional response bodies via Debugger API)
  • chrome_network_request - Send HTTP requests with browser cookies/context
πŸ” Content Analysis (3 tools)
  • chrome_read_page - Accessibility tree of visible elements (optional interactive-only filter)
  • chrome_get_web_content - Extract HTML/text content from pages
  • chrome_console - Capture console output (snapshot or buffer mode)
🎯 Interaction (8 tools)
  • chrome_computer - Drive mouse + keyboard, take screenshots
  • chrome_click_element - Click via selector / XPath / ref / coordinates
  • chrome_fill_or_select - Fill forms and select options
  • chrome_keyboard - Simulate keyboard input and shortcuts
  • chrome_request_element_selection - Ask the user to select elements (human-in-the-loop)
  • chrome_upload_file - Upload files to file inputs via CDP
  • chrome_handle_dialog - Handle alert/confirm/prompt dialogs
  • chrome_javascript - Execute JavaScript in a tab and return the result
πŸ“š Data Management (5 tools)
  • chrome_history - Search browser history with time filters
  • chrome_bookmark_search - Find bookmarks by keywords
  • chrome_bookmark_add - Add new bookmarks with folder support
  • chrome_bookmark_delete - Delete bookmarks
  • chrome_handle_download - Wait for and report browser downloads
⚑ Performance (3 tools)
  • performance_start_trace - Start a performance trace
  • performance_stop_trace - Stop the active trace
  • performance_analyze_insight - Summarize the last trace

πŸ§ͺ Usage Examples

AI helps you summarize webpage content and automatically control Excalidraw for drawing

prompt: excalidraw-prompt Instruction: Help me summarize the current page content, then draw a diagram to aid my understanding. https://www.youtube.com/watch?v=3fBPdUBWVz0

use.chrome-mcp.to.summarize.web.content.and.then.draw.with.Excalidraw.mp4

After analyzing the content of the image, the LLM automatically controls Excalidraw to replicate the image

prompt: excalidraw-prompt|content-analize Instruction: First, analyze the content of the image, and then replicate the image by combining the analysis with the content of the image. https://www.youtube.com/watch?v=tEPdHZBzbZk

chrome-mcpa.ae.a.a.c.a.a.a.c.a.mp4

AI automatically injects scripts and modifies webpage styles

prompt: modify-web-prompt Instruction: Help me modify the current page's style and remove advertisements. https://youtu.be/twI6apRKHsk

use.chrome-mcp.to.modify.web.style.mp4

AI automatically captures network requests for you

query: I want to know what the search API for Xiaohongshu is and what the response structure looks like

https://youtu.be/1hHKr7XKqnQ

1hHKr7XKqnQ.mp4

AI helps analyze your browsing history

query: Analyze my browsing history from the past month

https://youtu.be/jf2UZfrR2Vk

jf2UZfrR2Vk.mp4

Web page conversation

query: Translate and summarize the current web page https://youtu.be/FlJKS9UQyC8

FlJKS9UQyC8.mp4

AI automatically takes screenshots for you (web page screenshots)

query: Take a screenshot of Hugging Face's homepage https://youtu.be/7ycK6iksWi4

7ycK6iksWi4.mp4

AI automatically takes screenshots for you (element screenshots)

query: Capture the icon from Hugging Face's homepage https://youtu.be/ev8VivANIrk

ev8VivANIrk.mp4

AI helps manage bookmarks

query: Add the current page to bookmarks and put it in an appropriate folder

https://youtu.be/R_83arKmFTo

R_83arKmFTo.mp4

Automatically close web pages

query: Close all shadcn-related web pages

https://youtu.be/2wzUT6eNVg4

2wzUT6eNVg4.mp4

🀝 Contributing

We welcome contributions! Please see CONTRIBUTING.md for detailed guidelines.

🚧 Future Roadmap

We have exciting plans for the future development of Chrome MCP Server:

  • Authentication
  • Recording and Playback
  • Workflow Automation
  • Enhanced Browser Support (Firefox Extension)

Want to contribute to any of these features? Check out our Contributing Guide and join our development community!

🐍 Python Bridge

The mcp-chrome-bridge is a Python-based MCP server that bridges your Chrome extension with AI assistants.

Features

  • Pure Python implementation - No Node.js required
  • Streamable HTTP/SSE support
  • WebSocket bridge for extension communication
  • Automatic reconnection handling
  • Comprehensive logging

Commands

# Start the bridge server
mcp-chrome-bridge

# View help
mcp-chrome-bridge --help

Logs

Logs are output to stdout/stderr. Key log messages include:

  • Extension connected/disconnected - Extension connection status
  • Starting MCP HTTP/SSE Server on port 12306 - HTTP server started
  • Starting WebSocket Bridge on port 12307 - WebSocket server started

πŸ“„ License

This project is licensed under the MIT License - see the LICENSE file for details.

πŸ“š More Documentation

πŸ”§ Troubleshooting

Extension not connecting

  • Check that the Python bridge is running: mcp-chrome-bridge
  • Verify WebSocket connection on port 12307
  • Check logs for connection events

Module not found

  • Ensure you installed from the correct subdirectory: pip install -e app/bridge-python
  • Verify installation: pip show mcp-chrome-bridge

About

Chrome MCP Server is a Chrome extension-based Model Context Protocol (MCP) server that exposes your Chrome browser functionality to AI assistants like Claude, enabling complex browser automation, content analysis, and semantic search.

Resources

Contributing

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages

0