[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-72678":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},72678,"mcp-feedback-enhanced","Minidoracat\u002Fmcp-feedback-enhanced","Minidoracat","Enhanced MCP server for interactive user feedback and command execution in AI-assisted development, featuring dual interface support (Web UI and Desktop Application) with intelligent environment detection and cross-platform compatibility.","",null,"JavaScript",3792,352,21,75,0,4,6,9,12,71.54,"Other",false,"main",true,[],"2026-06-12 04:01:06","# MCP Feedback Enhanced\n\n**🌐 Language \u002F 語言切換:** **English** | [繁體中文](README.zh-TW.md) | [简体中文](README.zh-CN.md)\n\n**Original Author:** [Fábio Ferreira](https:\u002F\u002Fx.com\u002Ffabiomlferreira) | [Original Project](https:\u002F\u002Fgithub.com\u002Fnoopstudios\u002Finteractive-feedback-mcp) ⭐\n**Enhanced Fork:** [Minidoracat](https:\u002F\u002Fgithub.com\u002FMinidoracat)\n**UI Design Reference:** [sanshao85\u002Fmcp-feedback-collector](https:\u002F\u002Fgithub.com\u002Fsanshao85\u002Fmcp-feedback-collector)\n\n## 🎯 Core Concept\n\nThis is an [MCP server](https:\u002F\u002Fmodelcontextprotocol.io\u002F) that establishes **feedback-oriented development workflows**, providing **Web UI and Desktop Application** dual interface options, perfectly adapting to local, **SSH Remote environments**, and **WSL (Windows Subsystem for Linux) environments**. By guiding AI to confirm with users rather than making speculative operations, it can consolidate multiple tool calls into a single feedback-oriented request, dramatically reducing platform costs and improving development efficiency.\n\n**🌐 Dual Interface Architecture Advantages:**\n- 🖥️ **Desktop Application**: Native cross-platform desktop experience, supporting Windows, macOS, Linux\n- 🌐 **Web UI**: No GUI dependencies required, suitable for remote and WSL environments\n- 🔧 **Flexible Deployment**: Choose the most suitable interface mode based on environment requirements\n- 📦 **Unified Functionality**: Both interfaces provide exactly the same functional experience\n\n**🖥️ Desktop Application:** v2.5.0 introduces cross-platform desktop application support based on Tauri framework, supporting Windows, macOS, and Linux platforms with native desktop experience.\n\n**Supported Platforms:** [Cursor](https:\u002F\u002Fwww.cursor.com) | [Cline](https:\u002F\u002Fcline.bot) | [Windsurf](https:\u002F\u002Fwindsurf.com) | [Augment](https:\u002F\u002Fwww.augmentcode.com) | [Trae](https:\u002F\u002Fwww.trae.ai)\n\n### 🔄 Workflow\n1. **AI Call** → `mcp-feedback-enhanced` tool\n2. **Interface Launch** → Auto-open desktop application or browser interface (based on configuration)\n3. **Smart Interaction** → Prompt selection, text input, image upload, auto-submit\n4. **Real-time Feedback** → WebSocket connection delivers information to AI instantly\n5. **Session Tracking** → Auto-record session history and statistics\n6. **Process Continuation** → AI adjusts behavior or ends task based on feedback\n\n## 🌟 Key Features\n\n### 🖥️ Dual Interface Support\n- **Desktop Application**: Cross-platform native application based on Tauri, supporting Windows, macOS, Linux\n- **Web UI Interface**: Lightweight browser interface suitable for remote and WSL environments\n- **Automatic Environment Detection**: Intelligently recognizes SSH Remote, WSL and other special environments\n- **Unified Feature Experience**: Both interfaces provide exactly the same functionality\n\n### 📝 Smart Workflow\n- **Prompt Management**: CRUD operations for common prompts, usage statistics, intelligent sorting\n- **Auto-Timed Submit**: 1-86400 second flexible timer, supports pause, resume, cancel with new pause\u002Fresume button controls\n- **Auto Command Execution** (v2.6.0): Automatically execute preset commands after creating new sessions or commits for improved development efficiency\n- **Session Management & Tracking**: Local file storage, privacy controls, history export (supports JSON, CSV, Markdown formats), real-time statistics, flexible timeout settings\n- **Connection Monitoring**: WebSocket status monitoring, auto-reconnection, quality indicators\n- **AI Work Summary Markdown Display**: Support for rich Markdown syntax rendering including headers, bold text, code blocks, lists, links and other formats for enhanced content readability\n\n### 🎨 Modern Experience\n- **Responsive Design**: Adapts to different screen sizes, modular JavaScript architecture\n- **Audio Notifications**: Built-in multiple sound effects, custom audio upload support, volume control\n- **System Notifications** (v2.6.0): System-level real-time alerts for important events (like auto-commit, session timeout)\n- **Smart Memory**: Input box height memory, one-click copy, persistent settings\n- **Multi-language Support**: Traditional Chinese, English, Simplified Chinese, instant switching\n\n### 🖼️ Images & Media\n- **Full Format Support**: PNG, JPG, JPEG, GIF, BMP, WebP\n- **Convenient Upload**: Drag & drop files, clipboard paste (Ctrl+V)\n- **Unlimited Processing**: Support for any size images, automatic intelligent processing\n\n## 🌐 Interface Preview\n\n### Web UI Interface (v2.5.0 - Desktop Application Support)\n\n\u003Cdiv align=\"center\">\n  \u003Cimg src=\"docs\u002Fen\u002Fimages\u002Fweb1.png\" width=\"400\" alt=\"Web UI Main Interface - Prompt Management & Auto Submit\" \u002F>\n\u003C\u002Fdiv>\n\n\u003Cdetails>\n\u003Csummary>📱 Click to view complete interface screenshots\u003C\u002Fsummary>\n\n\u003Cdiv align=\"center\">\n  \u003Cimg src=\"docs\u002Fen\u002Fimages\u002Fweb2.jpeg\" width=\"800\" alt=\"Web UI Complete Interface - Session Management & Settings\" \u002F>\n\u003C\u002Fdiv>\n\n\u003C\u002Fdetails>\n\n*Web UI Interface - Supports desktop application and Web interface, providing prompt management, auto-submit, session tracking and other smart features*\n\n### Desktop Application Interface (v2.5.0 New Feature)\n\n\u003Cdiv align=\"center\">\n  \u003Cimg src=\"docs\u002Fen\u002Fimages\u002Fdesktop1.png\" width=\"600\" alt=\"Desktop Application - Native Cross-platform Desktop Experience\" \u002F>\n\u003C\u002Fdiv>\n\n*Desktop Application - Native cross-platform desktop application based on Tauri framework, supporting Windows, macOS, Linux with exactly the same functionality as Web UI*\n\n**Shortcut Support**\n- `Ctrl+Enter`（Windows\u002FLinux）\u002F `Cmd+Enter`（macOS）：Submit feedback (both main keyboard and numeric keypad supported)\n- `Ctrl+V`（Windows\u002FLinux）\u002F `Cmd+V`（macOS）：Direct paste clipboard images\n- `Ctrl+I`（Windows\u002FLinux）\u002F `Cmd+I`（macOS）：Quick focus input box (Thanks @penn201500)\n\n## 🚀 Quick Start\n\n### 1. Installation & Testing\n```bash\n# Install uv (if not already installed)\npip install uv\n```\n\n### 2. Configure MCP\n**Basic Configuration** (suitable for most users):\n```json\n{\n  \"mcpServers\": {\n    \"mcp-feedback-enhanced\": {\n      \"command\": \"uvx\",\n      \"args\": [\"mcp-feedback-enhanced@latest\"],\n      \"timeout\": 600,\n      \"autoApprove\": [\"interactive_feedback\"]\n    }\n  }\n}\n```\n\n**Advanced Configuration** (requires custom environment):\n```json\n{\n  \"mcpServers\": {\n    \"mcp-feedback-enhanced\": {\n      \"command\": \"uvx\",\n      \"args\": [\"mcp-feedback-enhanced@latest\"],\n      \"timeout\": 600,\n      \"env\": {\n        \"MCP_DEBUG\": \"false\",\n        \"MCP_WEB_HOST\": \"127.0.0.1\",\n        \"MCP_WEB_PORT\": \"8765\",\n        \"MCP_LANGUAGE\": \"en\"\n      },\n      \"autoApprove\": [\"interactive_feedback\"]\n    }\n  }\n}\n```\n\n**Desktop Application Configuration** (v2.5.0 new feature - using native desktop application):\n```json\n{\n  \"mcpServers\": {\n    \"mcp-feedback-enhanced\": {\n      \"command\": \"uvx\",\n      \"args\": [\"mcp-feedback-enhanced@latest\"],\n      \"timeout\": 600,\n      \"env\": {\n        \"MCP_DESKTOP_MODE\": \"true\",\n        \"MCP_WEB_HOST\": \"127.0.0.1\",\n        \"MCP_WEB_PORT\": \"8765\",\n        \"MCP_DEBUG\": \"false\"\n      },\n      \"autoApprove\": [\"interactive_feedback\"]\n    }\n  }\n}\n```\n\n**Configuration File Examples**:\n- Desktop Mode: [examples\u002Fmcp-config-desktop.json](examples\u002Fmcp-config-desktop.json)\n- Web Mode: [examples\u002Fmcp-config-web.json](examples\u002Fmcp-config-web.json)\n\n### 3. Prompt Engineering Setup\nFor optimal results, add the following rules to your AI assistant:\n\n```\n# MCP Interactive Feedback Rules\n\nfollow mcp-feedback-enhanced instructions\n```\n\n## ⚙️ Advanced Settings\n\n### Environment Variables\n| Variable | Purpose | Values | Default |\n|----------|---------|--------|---------|\n| `MCP_DEBUG` | Debug mode | `true`\u002F`false` | `false` |\n| `MCP_WEB_HOST` | Web UI host binding | IP address or hostname | `127.0.0.1` |\n| `MCP_WEB_PORT` | Web UI port | `1024-65535` | `8765` |\n| `MCP_DESKTOP_MODE` | Desktop application mode | `true`\u002F`false` | `false` |\n| `MCP_LANGUAGE` | Force UI language | `zh-TW`\u002F`zh-CN`\u002F`en` | Auto-detect |\n\n**`MCP_WEB_HOST` Explanation**:\n- `127.0.0.1` (default): Local access only, higher security\n- `0.0.0.0`: Allow remote access, suitable for SSH remote development environments\n\n**`MCP_LANGUAGE` Explanation**:\n- Used to force the interface language, overriding automatic system detection\n- Supported language codes:\n  - `zh-TW`: Traditional Chinese\n  - `zh-CN`: Simplified Chinese\n  - `en`: English\n- Language detection priority:\n  1. User-saved language settings in the interface (highest priority)\n  2. `MCP_LANGUAGE` environment variable\n  3. System environment variables (LANG, LC_ALL, etc.)\n  4. System default language\n  5. Fallback to default language (Traditional Chinese)\n\n### Testing Options\n```bash\n# Version check\nuvx mcp-feedback-enhanced@latest version       # Check version\n\n# Interface testing\nuvx mcp-feedback-enhanced@latest test --web    # Test Web UI (auto continuous running)\nuvx mcp-feedback-enhanced@latest test --desktop # Test desktop application (v2.5.0 new feature)\n\n# Debug mode\nMCP_DEBUG=true uvx mcp-feedback-enhanced@latest test\n\n# Specify language for testing\nMCP_LANGUAGE=en uvx mcp-feedback-enhanced@latest test --web    # Force English interface\nMCP_LANGUAGE=zh-TW uvx mcp-feedback-enhanced@latest test --web  # Force Traditional Chinese\nMCP_LANGUAGE=zh-CN uvx mcp-feedback-enhanced@latest test --web  # Force Simplified Chinese\n```\n\n### Developer Installation\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002FMinidoracat\u002Fmcp-feedback-enhanced.git\ncd mcp-feedback-enhanced\nuv sync\n```\n\n**Local Testing Methods**\n```bash\n# Functional testing\nmake test-func                                           # Standard functional testing\nmake test-web                                            # Web UI testing (continuous running)\nmake test-desktop-func                                   # Desktop application functional testing\n\n# Or use direct commands\nuv run python -m mcp_feedback_enhanced test              # Standard functional testing\nuvx --no-cache --with-editable . mcp-feedback-enhanced test --web   # Web UI testing (continuous running)\nuvx --no-cache --with-editable . mcp-feedback-enhanced test --desktop # Desktop application testing\n\n# Desktop application build (v2.5.0 new feature)\nmake build-desktop                                       # Build desktop application (debug mode)\nmake build-desktop-release                               # Build desktop application (release mode)\nmake test-desktop                                        # Test desktop application\nmake clean-desktop                                       # Clean desktop build artifacts\n\n# Unit testing\nmake test                                                # Run all unit tests\nmake test-fast                                          # Fast testing (skip slow tests)\nmake test-cov                                           # Test and generate coverage report\n\n# Code quality checks\nmake check                                              # Complete code quality check\nmake quick-check                                        # Quick check and auto-fix\n```\n\n**Testing Descriptions**\n- **Functional Testing**: Test complete MCP tool functionality workflow\n- **Unit Testing**: Test individual module functionality\n- **Coverage Testing**: Generate HTML coverage report to `htmlcov\u002F` directory\n- **Quality Checks**: Include linting, formatting, type checking\n\n## 🆕 Version History\n\n📋 **Complete Version History:** [RELEASE_NOTES\u002FCHANGELOG.en.md](RELEASE_NOTES\u002FCHANGELOG.en.md)\n\n### Latest Version Highlights (v2.6.0)\n- 🚀 **Auto Command Execution**: Automatically execute preset commands after creating new sessions or commits, improving workflow efficiency\n- 📊 **Session Export Feature**: Support exporting session records to multiple formats for easy sharing and archiving\n- ⏸️ **Auto-commit Control**: Added pause and resume buttons for better control over auto-commit timing\n- 🔔 **System Notifications**: System-level notifications for important events with real-time alerts\n- ⏱️ **Session Timeout Optimization**: Redesigned session management with more flexible configuration options\n- 🌏 **I18n Enhancement**: Refactored internationalization architecture with full multilingual support for notifications\n- 🎨 **UI Simplification**: Significantly simplified user interface for improved user experience\n\n## 🐛 Common Issues\n\n### 🌐 SSH Remote Environment Issues\n**Q: Browser cannot launch or access in SSH Remote environment**\nA: Two solutions available:\n\n**Solution 1: Environment Variable Setting (v2.5.5 Recommended)**\nSet `\"MCP_WEB_HOST\": \"0.0.0.0\"` in MCP configuration to allow remote access:\n```json\n{\n  \"mcpServers\": {\n    \"mcp-feedback-enhanced\": {\n      \"command\": \"uvx\",\n      \"args\": [\"mcp-feedback-enhanced@latest\"],\n      \"timeout\": 600,\n      \"env\": {\n        \"MCP_WEB_HOST\": \"0.0.0.0\",\n        \"MCP_WEB_PORT\": \"8765\"\n      },\n      \"autoApprove\": [\"interactive_feedback\"]\n    }\n  }\n}\n```\nThen open in local browser: `http:\u002F\u002F[remote-host-IP]:8765`\n\n**Solution 2: SSH Port Forwarding (Traditional Method)**\n1. Use default configuration (`MCP_WEB_HOST`: `127.0.0.1`)\n2. Set up SSH port forwarding:\n   - **VS Code Remote SSH**: Press `Ctrl+Shift+P` → \"Forward a Port\" → Enter `8765`\n   - **Cursor SSH Remote**: Manually add port forwarding rule (port 8765)\n3. Open in local browser: `http:\u002F\u002Flocalhost:8765`\n\nFor detailed solutions, refer to: [SSH Remote Environment Usage Guide](docs\u002Fen\u002Fssh-remote\u002Fbrowser-launch-issues.md)\n\n**Q: Why am I not receiving new MCP feedback?**\nA: Likely a WebSocket connection issue. **Solution**: Directly refresh the browser page.\n\n**Q: Why isn't MCP being called?**\nA: Please confirm MCP tool status shows green light. **Solution**: Repeatedly toggle MCP tool on\u002Foff, wait a few seconds for system reconnection.\n\n**Q: Augment cannot start MCP**\nA: **Solution**: Completely close and restart VS Code or Cursor, reopen the project.\n\n### 🔧 General Issues\n**Q: How to use desktop application?**\nA: v2.5.0 introduces cross-platform desktop application support. Set `\"MCP_DESKTOP_MODE\": \"true\"` in MCP configuration to enable:\n```json\n{\n  \"mcpServers\": {\n    \"mcp-feedback-enhanced\": {\n      \"command\": \"uvx\",\n      \"args\": [\"mcp-feedback-enhanced@latest\"],\n      \"timeout\": 600,\n      \"env\": {\n        \"MCP_DESKTOP_MODE\": \"true\",\n        \"MCP_WEB_PORT\": \"8765\"\n      },\n      \"autoApprove\": [\"interactive_feedback\"]\n    }\n  }\n}\n```\n**Configuration File Example**: [examples\u002Fmcp-config-desktop.json](examples\u002Fmcp-config-desktop.json)\n\n**Q: How to use legacy PyQt6 GUI interface?**\nA: v2.4.0 completely removed PyQt6 GUI dependencies. To use legacy GUI, specify v2.3.0 or earlier: `uvx mcp-feedback-enhanced@2.3.0`\n**Note**: Legacy versions don't include new features (prompt management, auto-submit, session management, desktop application, etc.).\n\n**Q: \"Unexpected token 'D'\" error appears**\nA: Debug output interference. Set `MCP_DEBUG=false` or remove the environment variable.\n\n**Q: Chinese character garbled text**\nA: Fixed in v2.0.3. Update to latest version: `uvx mcp-feedback-enhanced@latest`\n\n**Q: Window disappears or positioning errors in multi-screen environment**\nA: Fixed in v2.1.1. Go to \"⚙️ Settings\" tab, check \"Always show window at primary screen center\" to resolve. Especially suitable for T-shaped screen arrangements and other complex multi-screen configurations.\n\n**Q: Image upload failure**\nA: Check file format (PNG\u002FJPG\u002FJPEG\u002FGIF\u002FBMP\u002FWebP). System supports any size image files.\n\n**Q: Web UI cannot start**\nA: Check firewall settings or try using different ports.\n\n**Q: UV Cache occupies too much disk space**\nA: Due to frequent use of `uvx` commands, cache may accumulate to tens of GB. Regular cleanup recommended:\n```bash\n# View cache size and detailed information\npython scripts\u002Fcleanup_cache.py --size\n\n# Preview cleanup content (no actual cleanup)\npython scripts\u002Fcleanup_cache.py --dry-run\n\n# Execute standard cleanup\npython scripts\u002Fcleanup_cache.py --clean\n\n# Force cleanup (attempts to close related programs, solving Windows file occupation issues)\npython scripts\u002Fcleanup_cache.py --force\n\n# Or directly use uv command\nuv cache clean\n```\nFor detailed instructions, refer to: [Cache Management Guide](docs\u002Fen\u002Fcache-management.md)\n\n**Q: AI models cannot parse images**\nA: Various AI models (including Gemini Pro 2.5, Claude, etc.) may have instability in image parsing, sometimes correctly recognizing and sometimes unable to parse uploaded image content. This is a known limitation of AI visual understanding technology. Recommendations:\n1. Ensure good image quality (high contrast, clear text)\n2. Try uploading multiple times, retries usually succeed\n3. If parsing continues to fail, try adjusting image size or format\n\n## 🙏 Acknowledgments\n\n### 🌟 Support Original Author\n**Fábio Ferreira** - [X @fabiomlferreira](https:\u002F\u002Fx.com\u002Ffabiomlferreira)\n**Original Project:** [noopstudios\u002Finteractive-feedback-mcp](https:\u002F\u002Fgithub.com\u002Fnoopstudios\u002Finteractive-feedback-mcp)\n\nIf you find it useful, please:\n- ⭐ [Star the original project](https:\u002F\u002Fgithub.com\u002Fnoopstudios\u002Finteractive-feedback-mcp)\n- 📱 [Follow the original author](https:\u002F\u002Fx.com\u002Ffabiomlferreira)\n\n### Design Inspiration\n**sanshao85** - [mcp-feedback-collector](https:\u002F\u002Fgithub.com\u002Fsanshao85\u002Fmcp-feedback-collector)\n\n### Contributors\n**penn201500** - [GitHub @penn201500](https:\u002F\u002Fgithub.com\u002Fpenn201500)\n- 🎯 Auto-focus input box feature ([PR #39](https:\u002F\u002Fgithub.com\u002FMinidoracat\u002Fmcp-feedback-enhanced\u002Fpull\u002F39))\n\n**leo108** - [GitHub @leo108](https:\u002F\u002Fgithub.com\u002Fleo108)\n- 🌐 SSH Remote Development Support (`MCP_WEB_HOST` environment variable) ([PR #113](https:\u002F\u002Fgithub.com\u002FMinidoracat\u002Fmcp-feedback-enhanced\u002Fpull\u002F113))\n\n**Alsan** - [GitHub @Alsan](https:\u002F\u002Fgithub.com\u002FAlsan)\n- 🍎 macOS PyO3 Compilation Configuration Support ([PR #93](https:\u002F\u002Fgithub.com\u002FMinidoracat\u002Fmcp-feedback-enhanced\u002Fpull\u002F93))\n\n**fireinice** - [GitHub @fireinice](https:\u002F\u002Fgithub.com\u002Ffireinice)\n- 📝 Tool Documentation Optimization (LLM instructions moved to docstring) ([PR #105](https:\u002F\u002Fgithub.com\u002FMinidoracat\u002Fmcp-feedback-enhanced\u002Fpull\u002F105))\n\n### Community Support\n- **Discord:** [https:\u002F\u002Fdiscord.gg\u002FGur2V67](https:\u002F\u002Fdiscord.gg\u002FGur2V67)\n- **Issues:** [GitHub Issues](https:\u002F\u002Fgithub.com\u002FMinidoracat\u002Fmcp-feedback-enhanced\u002Fissues)\n\n## 📄 License\n\nMIT License - See [LICENSE](LICENSE) file for details\n\n## 📈 Star History\n\n[![Star History Chart](https:\u002F\u002Fapi.star-history.com\u002Fsvg?repos=Minidoracat\u002Fmcp-feedback-enhanced&type=Date)](https:\u002F\u002Fstar-history.com\u002F#Minidoracat\u002Fmcp-feedback-enhanced&Date)\n\n---\n**🌟 Welcome to Star and share with more developers!**\n","MCP Feedback Enhanced 是一个增强版的MCP服务器，用于在AI辅助开发中实现交互式用户反馈和命令执行。它支持Web UI和桌面应用程序双界面，具备智能环境检测和跨平台兼容性。项目核心功能包括通过引导AI与用户确认来减少不必要的操作、整合多个工具调用为单一反馈请求，从而大幅降低平台成本并提高开发效率。其灵活部署选项允许根据实际需求选择最适合的界面模式，同时保证两种界面提供一致的功能体验。该项目特别适合需要在本地、SSH远程或WSL环境下进行高效协作开发的场景使用。",2,"2026-06-11 03:43:08","high_star"]