mcp-feedback-collector

# 🎯 MCP Feedback Collector A modern Model Context Protocol (MCP) server that provides interactive user feedback collection for AI assistants.    ## Configuration in cursor rules “Whenever you want to ask a question, always call the MCP. Whenever you’re about to complete a user request, call the MCP instead of simply ending the process. Keep calling MCP until the user’s feedback is empty, then end the request. mcp-feedback-collector.collect_feedback” ## Related Tutorial Links YouTube: https://youtu.be/aYtGm1xHNXI Bilibili: https://www.bilibili.com/video/BV1J6jyzQE8P/ ## Node.js Version Released https://github.com/sanshao85/mcp-feedback-collector-web Supports remote server usage for a more powerful experience! ## ✨ Main Features - 🎨 **Modern Interface** - A beautiful 700x800 pixel GUI that supports a Chinese interface. - 📷 **Multi-Image Support** - Select multiple images at once, supporting file selection and clipboard paste. - 💬 **Flexible Feedback** - Supports pure text, pure images, or a combination of text and images for feedback. - ⚡ **Zero Configuration Installation** - One-click installation using uvx, no complex configuration required. - 🔧 **Smart Timeout** - Configurable dialog box timeout to avoid interruptions during operations. ## 🚀 Quick Start ### 1. Install uvx ```bash pip install uvx ``` ### 2. Configure Claude Desktop Add the following to `claude_desktop_config.json`: ```json { "mcpServers": { "mcp-feedback-collector": { "command": "uvx", "args": ["mcp-feedback-collector"], "env": { "PYTHONIOENCODING": "utf-8", "MCP_DIALOG_TIMEOUT": "600" } } } } ``` ### 3. Restart Claude Desktop After configuration, restart Claude Desktop to use it. ## 🛠️ Core Functions ### collect_feedback() The main tool for collecting user feedback, allowing AI to report work content while users provide text and image feedback. ```python # Example of AI calling result = collect_feedback("I have completed the code optimization work...") ``` ### pick_image() A quick image selection tool for single image selection scenarios. ### get_image_info() Retrieve detailed information about image files (format, dimensions, size, etc.). ## 🖼️ Interface Preview ``` 🎯 Work Completion Report and Feedback Collection ┌─────────────────────────────────────────┐ │ 📋 AI Work Completion Report │ │ ┌─────────────────────────────────────┐ │ │ │ [AI reported work content displayed here] │ │ │ └─────────────────────────────────────┘ │ └─────────────────────────────────────────┘ ┌─────────────────────────────────────────┐ │ 💬 Your Text Feedback (optional) │ │ ┌─────────────────────────────────────┐ │ │ │ [Multi-line text input area] │ │ │ └─────────────────────────────────────┘ │ └─────────────────────────────────────────┘ ┌─────────────────────────────────────────┐ │ 🖼️ Image Feedback (optional, supports multiple) │ │ [📁 Select File] [📋 Paste] [❌ Clear] │ │ [Image thumbnail preview area] │ └─────────────────────────────────────────┘ [✅ Submit Feedback] [❌ Cancel] ``` ## ⚙️ Configuration Instructions ### Timeout Settings - `MCP_DIALOG_TIMEOUT`: Dialog box wait time (seconds) - Default: 300 seconds (5 minutes) - Recommended: 600 seconds (10 minutes) - Complex operations: 1200 seconds (20 minutes) ### Supported Image Formats PNG, JPG, JPEG, GIF, BMP, WebP ## 💡 Use Cases - ✅ Collect user evaluations after AI completes tasks - ✅ Gather detailed feedback including screenshots - ✅ Obtain user opinions on code/design - ✅ Collect bug reports and improvement suggestions ## 🔧 Tech Stack - **MCP Framework**: FastMCP - **GUI**: tkinter + PIL - **Multithreading**: threading + queue - **Image Processing**: Pillow ## 📝 Changelog ### v2.0.0 (2025-05-28) - 🎨 Brand new modern UI design - 📷 Support for simultaneous submission of multiple images - 🖼️ Horizontal scrolling image preview - 💫 Colorful buttons and icons - 🔧 Optimized user experience ## 📄 License MIT License - See [LICENSE](LICENSE) file for details. ## 🤝 Contribution Feel free to submit Issues and Pull Requests! --- **Make AI interactions with users more efficient and intuitive!** 🎯 ## Thank You for Your Support https://api.ssopen.top/ API proxy station, 290+ AI large models, official cost one-seventh, supports high concurrency!