[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-73455":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":10,"rankLanguage":10,"license":22,"archived":23,"fork":23,"defaultBranch":24,"hasWiki":25,"hasPages":23,"topics":26,"createdAt":10,"pushedAt":10,"updatedAt":27,"readmeContent":28,"aiSummary":29,"trendingCount":16,"starSnapshotCount":16,"syncStatus":30,"lastSyncTime":31,"discoverSource":32},73455,"mcp-chrome","hangwin\u002Fmcp-chrome","hangwin","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.","",null,"TypeScript",11885,1066,48,189,0,30,129,293,90,44.08,"MIT License",false,"master",true,[],"2026-06-12 02:03:13","# Chrome MCP Server 🚀\n\n[![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fhangwin\u002Fmcp-chrome)](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fhangwin\u002Fmcp-chrome)\n[![License: MIT](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-MIT-yellow.svg)](https:\u002F\u002Fopensource.org\u002Flicenses\u002FMIT)\n[![TypeScript](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FTypeScript-5.8+-blue.svg)](https:\u002F\u002Fwww.typescriptlang.org\u002F)\n[![Chrome Extension](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FChrome-Extension-green.svg)](https:\u002F\u002Fdeveloper.chrome.com\u002Fdocs\u002Fextensions\u002F)\n[![Release](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fv\u002Frelease\u002Fhangwin\u002Fmcp-chrome.svg)](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fv\u002Frelease\u002Fhangwin\u002Fmcp-chrome.svg)\n\n> 🌟 **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> The project is still in its early stages and is under intensive development. More features, stability improvements, and other enhancements will follow.\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## ✨ New Features(2025\u002F12\u002F30)\n\n- **A New Visual Editor for Claude Code & Codex**, for more detail here: [VisualEditor](docs\u002FVisualEditor.md)\n\n## ✨ Core Features\n\n- 😁 **Chatbot\u002FModel 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 >= 20.0.0 and pnpm\u002Fnpm\n- Chrome\u002FChromium browser\n\n### Installation Steps\n\n1. **Download the latest Chrome extension from GitHub**\n\nDownload link: https:\u002F\u002Fgithub.com\u002Fhangwin\u002Fmcp-chrome\u002Freleases\n\n2. **Install mcp-chrome-bridge globally**\n\nnpm\n\n```bash\nnpm install -g mcp-chrome-bridge\n```\n\npnpm\n\n```bash\n# Method 1: Enable scripts globally (recommended)\npnpm config set enable-pre-post-scripts true\npnpm install -g mcp-chrome-bridge\n\n# Method 2: Manual registration (if postinstall doesn't run)\npnpm install -g mcp-chrome-bridge\nmcp-chrome-bridge register\n```\n\n> Note: pnpm v7+ disables postinstall scripts by default for security. The `enable-pre-post-scripts` setting controls whether pre\u002Fpost install scripts run. If automatic registration fails, use the manual registration command above.\n\n3. **Load Chrome Extension**\n   - Open Chrome and go to `chrome:\u002F\u002Fextensions\u002F`\n   - Enable \"Developer mode\"\n   - Click \"Load unpacked\" and select `your\u002Fdowloaded\u002Fextension\u002Ffolder`\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:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F241e57b8-c55f-41a4-9188-0367293dc5bc\" \u002F>\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\n> Streamable HTTP connection method is recommended\n\n```json\n{\n  \"mcpServers\": {\n    \"chrome-mcp-server\": {\n      \"type\": \"streamableHttp\",\n      \"url\": \"http:\u002F\u002F127.0.0.1:12306\u002Fmcp\"\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: \u002FUsers\u002Fxxx\u002FLibrary\u002Fpnpm\u002Fglobal\u002F5\nThen your final path would be: \u002FUsers\u002Fxxx\u002FLibrary\u002Fpnpm\u002Fglobal\u002F5\u002Fnode_modules\u002Fmcp-chrome-bridge\u002Fdist\u002Fmcp\u002Fmcp-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        \"\u002FUsers\u002Fxxx\u002FLibrary\u002Fpnpm\u002Fglobal\u002F5\u002Fnode_modules\u002Fmcp-chrome-bridge\u002Fdist\u002Fmcp\u002Fmcp-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:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F48eefc0c-a257-4d3b-8bbe-d7ff716de2bf\" \u002F>\n\n## 🛠️ Available Tools\n\nComplete tool list: [Complete Tool List](docs\u002FTOOLS.md)\n\n\u003Cdetails>\n\u003Csummary>\u003Cstrong>📊 Browser Management (6 tools)\u003C\u002Fstrong>\u003C\u002Fsummary>\n\n- `get_windows_and_tabs` - List all browser windows and tabs\n- `chrome_navigate` - Navigate to URLs and control viewport\n- `chrome_switch_tab` - Switch the current active tab\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\u002Fdetails>\n\n\u003Cdetails>\n\u003Csummary>\u003Cstrong>📸 Screenshots & Visual (1 tool)\u003C\u002Fstrong>\u003C\u002Fsummary>\n\n- `chrome_screenshot` - Advanced screenshot capture with element targeting, full-page support, and custom dimensions\n\u003C\u002Fdetails>\n\n\u003Cdetails>\n\u003Csummary>\u003Cstrong>🌐 Network Monitoring (4 tools)\u003C\u002Fstrong>\u003C\u002Fsummary>\n\n- `chrome_network_capture_start\u002Fstop` - webRequest API network capture\n- `chrome_network_debugger_start\u002Fstop` - Debugger API with response bodies\n- `chrome_network_request` - Send custom HTTP requests\n\u003C\u002Fdetails>\n\n\u003Cdetails>\n\u003Csummary>\u003Cstrong>🔍 Content Analysis (4 tools)\u003C\u002Fstrong>\u003C\u002Fsummary>\n\n- `search_tabs_content` - AI-powered semantic search across browser tabs\n- `chrome_get_web_content` - Extract HTML\u002Ftext content from pages\n- `chrome_get_interactive_elements` - Find clickable elements\n- `chrome_console` - Capture and retrieve console output from browser tabs\n\u003C\u002Fdetails>\n\n\u003Cdetails>\n\u003Csummary>\u003Cstrong>🎯 Interaction (3 tools)\u003C\u002Fstrong>\u003C\u002Fsummary>\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\u002Fdetails>\n\n\u003Cdetails>\n\u003Csummary>\u003Cstrong>📚 Data Management (5 tools)\u003C\u002Fstrong>\u003C\u002Fsummary>\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\u002Fdetails>\n\n## 🧪 Usage Examples\n\n### AI helps you summarize webpage content and automatically control Excalidraw for drawing\n\nprompt: [excalidraw-prompt](prompt\u002Fexcalidraw-prompt.md)\nInstruction: Help me summarize the current page content, then draw a diagram to aid my understanding.\nhttps:\u002F\u002Fwww.youtube.com\u002Fwatch?v=3fBPdUBWVz0\n\nhttps:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002Ffd17209b-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\u002Fexcalidraw-prompt.md)|[content-analize](prompt\u002Fcontent-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.\nhttps:\u002F\u002Fwww.youtube.com\u002Fwatch?v=tEPdHZBzbZk\n\nhttps:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F60d12b1a-9b74-40f4-994c-95e8fa1fc8d3\n\n### AI automatically injects scripts and modifies webpage styles\n\nprompt: [modify-web-prompt](prompt\u002Fmodify-web.md)\nInstruction: Help me modify the current page's style and remove advertisements.\nhttps:\u002F\u002Fyoutu.be\u002FtwI6apRKHsk\n\nhttps:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F69cb561c-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:\u002F\u002Fyoutu.be\u002F1hHKr7XKqnQ\n\nhttps:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002Fdc7e5cab-b9af-4b9a-97ce-18e4837318d9\n\n### AI helps analyze your browsing history\n\nquery: Analyze my browsing history from the past month\n\nhttps:\u002F\u002Fyoutu.be\u002Fjf2UZfrR2Vk\n\nhttps:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F31b2e064-88c6-4adb-96d7-50748b826eae\n\n### Web page conversation\n\nquery: Translate and summarize the current web page\nhttps:\u002F\u002Fyoutu.be\u002FFlJKS9UQyC8\n\nhttps:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002Faa8ef2a1-2310-47e6-897a-769d85489396\n\n### AI automatically takes screenshots for you (web page screenshots)\n\nquery: Take a screenshot of Hugging Face's homepage\nhttps:\u002F\u002Fyoutu.be\u002F7ycK6iksWi4\n\nhttps:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F65c6eee2-6366-493d-a3bd-2b27529ff5b3\n\n### AI automatically takes screenshots for you (element screenshots)\n\nquery: Capture the icon from Hugging Face's homepage\nhttps:\u002F\u002Fyoutu.be\u002Fev8VivANIrk\n\nhttps:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002Fd0cf9785-c2fe-4729-a3c5-7f2b8b96fe0c\n\n### AI helps manage bookmarks\n\nquery: Add the current page to bookmarks and put it in an appropriate folder\n\nhttps:\u002F\u002Fyoutu.be\u002FR_83arKmFTo\n\nhttps:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F15a7d04c-0196-4b40-84c2-bafb5c26dfe0\n\n### Automatically close web pages\n\nquery: Close all shadcn-related web pages\n\nhttps:\u002F\u002Fyoutu.be\u002F2wzUT6eNVg4\n\nhttps:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F83de4008-bb7e-494d-9b0f-98325cfea592\n\n## 🤝 Contributing\n\nWe welcome contributions! Please see [CONTRIBUTING.md](docs\u002FCONTRIBUTING.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\u002FCONTRIBUTING.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\u002FARCHITECTURE.md) - Detailed technical architecture documentation\n- [TOOLS API](docs\u002FTOOLS.md) - Complete tool API documentation\n- [Troubleshooting](docs\u002FTROUBLESHOOTING.md) - Common issue solutions\n","Chrome MCP Server 是一个基于 Chrome 扩展的 Model Context Protocol (MCP) 服务器，它将你的 Chrome 浏览器功能暴露给像 Claude 这样的 AI 助手，实现复杂的浏览器自动化、内容分析和语义搜索。项目的核心功能包括支持多种聊天机器人或大语言模型控制浏览器、无缝集成用户的现有浏览器环境（配置、登录状态等）、完全本地化以确保用户隐私、流式 HTTP 连接方法、跨标签页上下文管理、内置向量数据库进行智能内容发现以及通过 WebAssembly SIMD 优化实现的高速 AI 计算。此外，它还提供了截图、网络监控、交互操作、书签管理和浏览历史记录等 20 多种工具。此项目适用于需要高效利用 AI 功能来增强日常浏览器使用体验的场景。",2,"2026-06-11 03:45:38","high_star"]