π Turn your Chrome browser into your intelligent assistant - Let AI take control of your browser, transforming it into a powerful AI-controlled automation tool.
π Documentation: English | δΈζ
The project is under active development. Python bridge now available - no Node.js required!
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.
- A New Visual Editor for Claude Code & Codex, for more detail here: VisualEditor
- π Chatbot/Model Agnostic: Let any LLM or chatbot client or agent you prefer automate your browser
- βοΈ Use Your Original Browser: Seamlessly integrate with your existing browser environment (your configurations, login states, etc.)
- π» Fully Local: Pure local MCP server ensuring user privacy
- π Streamable HTTP: Streamable HTTP connection method
- π Cross-Tab: Cross-tab context
- π§ Semantic Search: Built-in vector database for intelligent browser tab content discovery
- π Smart Content Analysis: AI-powered text extraction and similarity matching
- π 20+ Tools: Support for screenshots, network monitoring, interactive operations, bookmark management, browsing history, and 20+ other tools
- π SIMD-Accelerated AI: Custom WebAssembly SIMD optimization for 4-8x faster vector operations
| Comparison Dimension | Playwright-based MCP Server | Chrome Extension-based MCP Server |
|---|---|---|
| Resource Usage | β Requires launching independent browser process, installing Playwright dependencies, downloading browser binaries, etc. | β No need to launch independent browser process, directly utilizes user's already open Chrome browser |
| User Session Reuse | β Requires re-login | β Automatically uses existing login state |
| Browser Environment | β Clean environment lacks user settings | β Fully preserves user environment |
| API Access | β Full access to Chrome native APIs | |
| Startup Speed | β Requires launching browser process | β Only needs to activate extension |
| Response Speed | 50-200ms inter-process communication | β Faster |
- Node.js >= 20.0.0 and pnpm/npm
- Chrome/Chromium browser
- Clone the repository
git clone https://github.com/davincinewton/mcp-chrome-python.git
cd mcp-chrome-python- Install the Python bridge
From the repository root:
pip install -e app/bridge-pythonOr install from source without cloning:
pip install "mcp-chrome-bridge @ git+https://github.com/davincinewton/mcp-chrome-python.git#subdirectory=app/bridge-python"-
Build the Chrome Extension
From the repository root:
pnpm install pnpm run build:shared pnpm run build:extension
-
Load Chrome Extension
pip uninstall mcp-chrome-bridgemcp-chrome-bridgeThe 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
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.
Complete tool list: Complete Tool List
π Browser Management (4 tools)
get_windows_and_tabs- List all browser windows and tabschrome_navigate- Navigate to URLs, refresh, or go back/forwardchrome_switch_tab- Switch the current active tabchrome_close_tabs- Close specific tabs
π 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-closedchrome_google_search- Deep Google search: resolves real URLs + captures article full text + key image URLs for the top-N results
πΈ Screenshots & Visual (2 tools)
chrome_screenshot- Screenshot with element targeting, full-page, custom dimensionschrome_gif_recorder- Record tab activity as an animated GIF
π 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
π 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 pageschrome_console- Capture console output (snapshot or buffer mode)
π― Interaction (8 tools)
chrome_computer- Drive mouse + keyboard, take screenshotschrome_click_element- Click via selector / XPath / ref / coordinateschrome_fill_or_select- Fill forms and select optionschrome_keyboard- Simulate keyboard input and shortcutschrome_request_element_selection- Ask the user to select elements (human-in-the-loop)chrome_upload_file- Upload files to file inputs via CDPchrome_handle_dialog- Handle alert/confirm/prompt dialogschrome_javascript- Execute JavaScript in a tab and return the result
π Data Management (5 tools)
chrome_history- Search browser history with time filterschrome_bookmark_search- Find bookmarks by keywordschrome_bookmark_add- Add new bookmarks with folder supportchrome_bookmark_delete- Delete bookmarkschrome_handle_download- Wait for and report browser downloads
β‘ Performance (3 tools)
performance_start_trace- Start a performance traceperformance_stop_trace- Stop the active traceperformance_analyze_insight- Summarize the last trace
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
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
query: I want to know what the search API for Xiaohongshu is and what the response structure looks like
1hHKr7XKqnQ.mp4
query: Analyze my browsing history from the past month
jf2UZfrR2Vk.mp4
query: Translate and summarize the current web page https://youtu.be/FlJKS9UQyC8
FlJKS9UQyC8.mp4
query: Take a screenshot of Hugging Face's homepage https://youtu.be/7ycK6iksWi4
7ycK6iksWi4.mp4
query: Capture the icon from Hugging Face's homepage https://youtu.be/ev8VivANIrk
ev8VivANIrk.mp4
query: Add the current page to bookmarks and put it in an appropriate folder
R_83arKmFTo.mp4
query: Close all shadcn-related web pages
2wzUT6eNVg4.mp4
We welcome contributions! Please see CONTRIBUTING.md for detailed guidelines.
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!
The mcp-chrome-bridge is a Python-based MCP server that bridges your Chrome extension with AI assistants.
- Pure Python implementation - No Node.js required
- Streamable HTTP/SSE support
- WebSocket bridge for extension communication
- Automatic reconnection handling
- Comprehensive logging
# Start the bridge server
mcp-chrome-bridge
# View help
mcp-chrome-bridge --helpLogs are output to stdout/stderr. Key log messages include:
Extension connected/disconnected- Extension connection statusStarting MCP HTTP/SSE Server on port 12306- HTTP server startedStarting WebSocket Bridge on port 12307- WebSocket server started
This project is licensed under the MIT License - see the LICENSE file for details.
- Architecture Design - Detailed technical architecture documentation
- TOOLS API - Complete tool API documentation
- Troubleshooting - Common issue solutions
- Check that the Python bridge is running:
mcp-chrome-bridge - Verify WebSocket connection on port 12307
- Check logs for connection events
- Ensure you installed from the correct subdirectory:
pip install -e app/bridge-python - Verify installation:
pip show mcp-chrome-bridge