{"id":28958403,"url":"https://github.com/hangwin/mcp-chrome","last_synced_at":"2025-06-23T23:01:43.712Z","repository":{"id":298164757,"uuid":"998796026","full_name":"hangwin/mcp-chrome","owner":"hangwin","description":"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.","archived":false,"fork":false,"pushed_at":"2025-06-16T19:10:03.000Z","size":20939,"stargazers_count":598,"open_issues_count":5,"forks_count":37,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-06-16T20:19:49.777Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"TypeScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/hangwin.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"docs/CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2025-06-09T09:07:06.000Z","updated_at":"2025-06-16T19:10:06.000Z","dependencies_parsed_at":"2025-06-09T19:33:54.577Z","dependency_job_id":null,"html_url":"https://github.com/hangwin/mcp-chrome","commit_stats":null,"previous_names":["hangwin/mcp-chrome"],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/hangwin/mcp-chrome","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hangwin%2Fmcp-chrome","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hangwin%2Fmcp-chrome/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hangwin%2Fmcp-chrome/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hangwin%2Fmcp-chrome/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/hangwin","download_url":"https://codeload.github.com/hangwin/mcp-chrome/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/hangwin%2Fmcp-chrome/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":261571302,"owners_count":23178762,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2025-06-23T23:00:51.536Z","updated_at":"2025-06-23T23:01:43.704Z","avatar_url":"https://github.com/hangwin.png","language":"TypeScript","funding_links":[],"categories":["MCP Servers \u0026 Tools","Model Context Protocol (MCP) Servers","TypeScript","📚 Projects (1974 total)","A01_文本生成_文本对话","MCP Ecosystem","Dev Tools (29)","AI应用","MCP Servers","Web \u0026 Search","ツール","MCP 服务器精选列表"],"sub_categories":["Browser \u0026 Automation","MCP Servers","大语言对话模型及数据","Servers","Browser and Web","MCPサーバー \u0026 ツール","🌐 浏览器自动化与网页交互"],"readme":"# Chrome MCP Server 🚀\n\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)\n[![TypeScript](https://img.shields.io/badge/TypeScript-5.8+-blue.svg)](https://www.typescriptlang.org/)\n[![Chrome Extension](https://img.shields.io/badge/Chrome-Extension-green.svg)](https://developer.chrome.com/docs/extensions/)\n\n\u003e 🌟 **Turn your Chrome browser into your intelligent assistant** - Let AI take control of your browser, transforming it into a powerful AI-controlled automation tool.\n\n**📖 Documentation**: [English](README.md) | [中文](README_zh.md)\n\n---\n\n## 🎯 What is Chrome MCP Server?\n\nChrome 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.\n\n## ✨ Core Features\n\n- 😁 **Chatbot/Model Agnostic**: Let any LLM or chatbot client or agent you prefer automate your browser\n- ⭐️ **Use Your Original Browser**: Seamlessly integrate with your existing browser environment (your configurations, login states, etc.)\n- 💻 **Fully Local**: Pure local MCP server ensuring user privacy\n- 🚄 **Streamable HTTP**: Streamable HTTP connection method\n- 🏎 **Cross-Tab**: Cross-tab context\n- 🧠 **Semantic Search**: Built-in vector database for intelligent browser tab content discovery\n- 🔍 **Smart Content Analysis**: AI-powered text extraction and similarity matching\n- 🌐 **20+ Tools**: Support for screenshots, network monitoring, interactive operations, bookmark management, browsing history, and 20+ other tools\n- 🚀 **SIMD-Accelerated AI**: Custom WebAssembly SIMD optimization for 4-8x faster vector operations\n\n## 🆚 Comparison with Similar Projects\n\n| Comparison Dimension    | Playwright-based MCP Server                                                                                               | Chrome Extension-based MCP Server                                                                      |\n| ----------------------- | ------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------ |\n| **Resource Usage**      | ❌ Requires launching independent browser process, installing Playwright dependencies, downloading browser binaries, etc. | ✅ No need to launch independent browser process, directly utilizes user's already open Chrome browser |\n| **User Session Reuse**  | ❌ Requires re-login                                                                                                      | ✅ Automatically uses existing login state                                                             |\n| **Browser Environment** | ❌ Clean environment lacks user settings                                                                                  | ✅ Fully preserves user environment                                                                    |\n| **API Access**          | ⚠️ Limited to Playwright API                                                                                              | ✅ Full access to Chrome native APIs                                                                   |\n| **Startup Speed**       | ❌ Requires launching browser process                                                                                     | ✅ Only needs to activate extension                                                                    |\n| **Response Speed**      | 50-200ms inter-process communication                                                                                      | ✅ Faster                                                                                              |\n\n## 🚀 Quick Start\n\n### Prerequisites\n\n- Node.js 18+ and pnpm\n- Chrome/Chromium browser\n\n### Installation Steps\n\n1. **Download the latest Chrome extension from GitHub**\n\nDownload link: https://github.com/hangwin/mcp-chrome/releases\n\n2. **Install mcp-chrome-bridge globally**\n\nnpm\n\n```bash\nnpm install -g mcp-chrome-bridge\n```\n\npnpm\n\n```bash\npnpm install -g mcp-chrome-bridge --unsafe-perm\n```\n\n\u003e Note: When using pnpm, the `--unsafe-perm` flag is required to ensure post-installation scripts run properly, which is necessary for registering the Native Messaging host.\n\n3. **Load Chrome Extension**\n   - Open Chrome and go to `chrome://extensions/`\n   - Enable \"Developer mode\"\n   - Click \"Load unpacked\" and select `your/dowloaded/extension/folder`\n   - Click the extension icon to open the plugin, then click connect to see the MCP configuration\n   \u003cimg width=\"475\" alt=\"Screenshot 2025-06-09 15 52 06\" src=\"https://github.com/user-attachments/assets/241e57b8-c55f-41a4-9188-0367293dc5bc\" /\u003e\n\n### Usage with MCP Protocol Clients\n\n#### Using Streamable HTTP Connection (👍🏻 Recommended)\n\nAdd the following configuration to your MCP client configuration (using CherryStudio as an example):\n\u003e Streamable HTTP connection method is recommended\n\n```json\n{\n  \"mcpServers\": {\n    \"chrome-mcp-server\": {\n      \"type\": \"streamableHttp\",\n      \"url\": \"http://127.0.0.1:12306/mcp\"\n    }\n  }\n}\n```\n\n#### Using STDIO Connection (Alternative)\n\nIf your client only supports stdio connection method, please use the following approach:\n\n1. First, check the installation location of the npm package you just installed\n\n```sh\n# npm check method\nnpm list -g mcp-chrome-bridge\n# pnpm check method\npnpm list -g mcp-chrome-bridge\n```\n\nAssuming the command above outputs the path: /Users/xxx/Library/pnpm/global/5\nThen your final path would be: /Users/xxx/Library/pnpm/global/5/node_modules/mcp-chrome-bridge/dist/mcp/mcp-server-stdio.js\n\n2. Replace the configuration below with the final path you just obtained\n\n```json\n{\n  \"mcpServers\": {\n    \"chrome-mcp-stdio\": {\n      \"command\": \"npx\",\n      \"args\": [\n        \"node\",\n        \"/Users/xxx/Library/pnpm/global/5/node_modules/mcp-chrome-bridge/dist/mcp/mcp-server-stdio.js\"\n      ]\n    }\n  }\n}\n```\n\neg：config in augment:\n\n\u003cimg width=\"494\" alt=\"截屏2025-06-22 22 11 25\" src=\"https://github.com/user-attachments/assets/48eefc0c-a257-4d3b-8bbe-d7ff716de2bf\" /\u003e\n\n## 🛠️ Available Tools\n\nComplete tool list: [Complete Tool List](docs/TOOLS.md)\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cstrong\u003e📊 Browser Management (6 tools)\u003c/strong\u003e\u003c/summary\u003e\n\n- `get_windows_and_tabs` - List all browser windows and tabs\n- `chrome_navigate` - Navigate to URLs and control viewport\n- `chrome_close_tabs` - Close specific tabs or windows\n- `chrome_go_back_or_forward` - Browser navigation control\n- `chrome_inject_script` - Inject content scripts into web pages\n- `chrome_send_command_to_inject_script` - Send commands to injected content scripts\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cstrong\u003e📸 Screenshots \u0026 Visual (1 tool)\u003c/strong\u003e\u003c/summary\u003e\n\n- `chrome_screenshot` - Advanced screenshot capture with element targeting, full-page support, and custom dimensions\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cstrong\u003e🌐 Network Monitoring (4 tools)\u003c/strong\u003e\u003c/summary\u003e\n\n- `chrome_network_capture_start/stop` - webRequest API network capture\n- `chrome_network_debugger_start/stop` - Debugger API with response bodies\n- `chrome_network_request` - Send custom HTTP requests\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cstrong\u003e🔍 Content Analysis (4 tools)\u003c/strong\u003e\u003c/summary\u003e\n\n- `search_tabs_content` - AI-powered semantic search across browser tabs\n- `chrome_get_web_content` - Extract HTML/text content from pages\n- `chrome_get_interactive_elements` - Find clickable elements\n- `chrome_console` - Capture and retrieve console output from browser tabs\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cstrong\u003e🎯 Interaction (3 tools)\u003c/strong\u003e\u003c/summary\u003e\n\n- `chrome_click_element` - Click elements using CSS selectors\n- `chrome_fill_or_select` - Fill forms and select options\n- `chrome_keyboard` - Simulate keyboard input and shortcuts\n\u003c/details\u003e\n\n\u003cdetails\u003e\n\u003csummary\u003e\u003cstrong\u003e📚 Data Management (5 tools)\u003c/strong\u003e\u003c/summary\u003e\n\n- `chrome_history` - Search browser history with time filters\n- `chrome_bookmark_search` - Find bookmarks by keywords\n- `chrome_bookmark_add` - Add new bookmarks with folder support\n- `chrome_bookmark_delete` - Delete bookmarks\n\u003c/details\u003e\n\n## 🧪 Usage Examples\n\n### AI helps you summarize webpage content and automatically control Excalidraw for drawing\n\nprompt: [excalidraw-prompt](prompt/excalidraw-prompt.md)\nInstruction: Help me summarize the current page content, then draw a diagram to aid my understanding.\n\nhttps://github.com/user-attachments/assets/fd17209b-303d-48db-9e5e-3717141df183\n\n### After analyzing the content of the image, the LLM automatically controls Excalidraw to replicate the image\n\nprompt: [excalidraw-prompt](prompt/excalidraw-prompt.md)|[content-analize](prompt/content-analize.md)\nInstruction: First, analyze the content of the image, and then replicate the image by combining the analysis with the content of the image.\n\nhttps://github.com/user-attachments/assets/60d12b1a-9b74-40f4-994c-95e8fa1fc8d3\n\n### AI automatically injects scripts and modifies webpage styles\n\nprompt: [modify-web-prompt](prompt/modify-web.md)\nInstruction: Help me modify the current page's style and remove advertisements.\n\nhttps://github.com/user-attachments/assets/69cb561c-2e1e-4665-9411-4a3185f9643e\n\n### AI automatically captures network requests for you\n\nquery: I want to know what the search API for Xiaohongshu is and what the response structure looks like\n\nhttps://github.com/user-attachments/assets/063f44ae-1754-46b6-b141-5988c86e4d96\n\n### AI helps analyze your browsing history\n\nquery: Analyze my browsing history from the past month\n\nhttps://github.com/user-attachments/assets/e7a35118-e50e-4b1c-a790-0878aa2505ab\n\n### Web page conversation\n\nquery: Translate and summarize the current web page\n\nhttps://github.com/user-attachments/assets/08aa86aa-7706-4df2-b400-576e2c7fcc7f\n\n### AI automatically takes screenshots for you (web page screenshots)\n\nquery: Take a screenshot of Hugging Face's homepage\n\nhttps://github.com/user-attachments/assets/b081e41b-6309-40d6-885b-0da01691b12e\n\n### AI automatically takes screenshots for you (element screenshots)\n\nquery: Capture the icon from Hugging Face's homepage\n\nhttps://github.com/user-attachments/assets/25657076-b84b-4459-a72f-90f896f06364\n\n### AI helps manage bookmarks\n\nquery: Add the current page to bookmarks and put it in an appropriate folder\n\nhttps://github.com/user-attachments/assets/73c1ea26-65fb-4b5e-b537-e32fa9bcfa52\n\n### Automatically close web pages\n\nquery: Close all shadcn-related web pages\n\nhttps://github.com/user-attachments/assets/ff160f48-58e0-4c76-a6b0-c4e1f91370c8\n\n## 🤝 Contributing\n\nWe welcome contributions! Please see [CONTRIBUTING.md](docs/CONTRIBUTING.md) for detailed guidelines.\n\n## 🚧 Future Roadmap\n\nWe have exciting plans for the future development of Chrome MCP Server:\n\n- [ ] Authentication\n- [ ] Recording and Playback\n- [ ] Workflow Automation\n- [ ] Enhanced Browser Support (Firefox Extension)\n\n---\n\n**Want to contribute to any of these features?** Check out our [Contributing Guide](docs/CONTRIBUTING.md) and join our development community!\n\n## 📄 License\n\nThis project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.\n\n## 📚 More Documentation\n\n- [Architecture Design](docs/ARCHITECTURE.md) - Detailed technical architecture documentation\n- [TOOLS API](docs/TOOLS.md) - Complete tool API documentation\n- [Troubleshooting](docs/TROUBLESHOOTING.md) - Common issue solutions\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhangwin%2Fmcp-chrome","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhangwin%2Fmcp-chrome","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhangwin%2Fmcp-chrome/lists"}