mcp-feedback-collector

# 🎯 MCP Feedback Collector A modern Model Context Protocol (MCP) server that provides interactive user feedback collection for AI assistants.    ## The following configuration can be done 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/ ## Nodejs version has been released https://github.com/sanshao85/mcp-feedback-collector-web Support remote server use, more powerful experience! ## ✨ Key Features - 🎨 **Modern Interface** - Beautiful 700x800 pixel GUI, supports Chinese interface - 📷 **Multi-Image Support** - Select multiple images simultaneously, supports file selection and clipboard pasting - 💬 **Flexible Feedback** - Supports pure text, pure image, or text + image combination feedback - ⚡ **Zero-Configuration Installation** - One-click installation using uvx, no complex configuration required - 🔧 **Intelligent Timeout** - Configurable dialog timeout to avoid operation interruption ## 🚀 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 Restart Claude Desktop after configuration to use. ## 🛠️ Core Functionality ### collect_feedback() The main tool for collecting user feedback, AI can report work content, and users can provide text and image feedback. ```python # AI call example result = collect_feedback("I have completed the code optimization...") ``` ### pick_image() Quick image selection tool for single image selection scenarios. ### get_image_info() Get detailed information about the image file (format, size, dimensions, 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 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 ## 💡 Usage Scenarios - ✅ Collect user evaluations after AI completes tasks - ✅ Collect detailed feedback including screenshots - ✅ Get user opinions on code/designs - ✅ Collect bug reports and improvement suggestions ## 🔧 Technology Stack - **MCP Framework**: FastMCP - **GUI**: tkinter + PIL - **Multithreading**: threading + queue - **Image Processing**: Pillow ## 📝 Changelog ### v2.0.0 (2025-05-28) - 🎨 New modern UI design - 📷 Multiple image submission support - 🖼️ Horizontal scrolling image preview - 💫 Colored buttons and icons - 🔧 Optimized user experience ## 📄 License MIT License - See [LICENSE](LICENSE) file for details ## 🤝 Contribution Welcome to submit Issues and Pull Requests! --- **Make AI and user interaction more efficient and intuitive!** 🎯 ## Thanks for your support https://api.ssopen.top/ API relay station, 290+AI large models, one-seventh of the official cost, support high concurrency!