MCP Feedback Enhanced

🌐 Language / 語言切換: English | 繁體中文 | 简体中文

Original Author: Fábio Ferreira | Original Project ⭐
Enhanced Fork: Minidoracat
UI Design Reference: sanshao85/mcp-feedback-collector

🎯 Core Concept

This is an MCP server that establishes feedback-oriented development workflows, perfectly adapting to local, SSH remote development 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.

Supported Platforms: Cursor | Cline | Windsurf | Augment | Trae

🔄 Workflow

AI Call → mcp-feedback-enhanced
Environment Detection → Auto-select appropriate interface
User Interaction → Command execution, text feedback, image upload
Feedback Delivery → Information returns to AI
Process Continuation → Adjust or end based on feedback

🌟 Key Features

🖥️ Dual Interface System

Qt GUI: Native experience for local environments, modular refactored design
Web UI: Modern interface for remote SSH and WSL environments, brand new architecture
Smart Switching: Auto-detect environment (local/remote/WSL) and choose optimal interface

🎨 Brand New Interface Design (v2.1.0)

Modular Architecture: Both GUI and Web UI adopt modular design
Centralized Management: Reorganized folder structure for easier maintenance
Modern Themes: Improved visual design and user experience
Responsive Layout: Adapts to different screen sizes and window dimensions

🖼️ Image Support

Format Support: PNG, JPG, JPEG, GIF, BMP, WebP
Upload Methods: Drag & drop files + clipboard paste (Ctrl+V)
Auto Processing: Smart compression to ensure 1MB limit compliance

🌏 Multi-language

Three Languages: English, Traditional Chinese, Simplified Chinese
Smart Detection: Auto-select based on system language
Live Switching: Change language directly within interface

✨ WSL Environment Support (v2.2.5 New Feature)

Auto Detection: Intelligently identifies WSL (Windows Subsystem for Linux) environments
Browser Integration: Automatically launches Windows browser in WSL environments
Multiple Launch Methods: Supports cmd.exe, powershell.exe, wslview and other browser launch methods
Seamless Experience: WSL users can directly use Web UI without additional configuration

🖥️ Interface Preview

Qt GUI Interface (Refactored Version)

Qt GUI Interface - Modular refactoring, supporting local environments

Web UI Interface (Refactored Version)

Web UI Interface - Brand new architecture, suitable for SSH Remote environments

Keyboard Shortcuts

Ctrl+Enter: Submit feedback (supports both main keyboard and numpad)
Ctrl+V: Directly paste clipboard images

🚀 Quick Start

1. Installation & Testing

# Install uv (if not already installed)
pip install uv

# Quick test
uvx mcp-feedback-enhanced@latest test

2. MCP Configuration

Basic Configuration (suitable for most users):

{
  "mcpServers": {
    "mcp-feedback-enhanced": {
      "command": "uvx",
      "args": ["mcp-feedback-enhanced@latest"],
      "timeout": 600,
      "autoApprove": ["interactive_feedback"]
    }
  }
}

Advanced Configuration (custom environment needed):

{
  "mcpServers": {
    "mcp-feedback-enhanced": {
      "command": "uvx",
      "args": ["mcp-feedback-enhanced@latest"],
      "timeout": 600,
      "env": {
        "FORCE_WEB": "true",
        "MCP_DEBUG": "false"
      },
      "autoApprove": ["interactive_feedback"]
    }
  }
}

3. Prompt Engineering Setup

For best results, add these rules to your AI assistant:

# MCP Interactive Feedback Rules

1. During any process, task, or conversation, whether asking, responding, or completing stage tasks, must call MCP mcp-feedback-enhanced.
2. When receiving user feedback, if feedback content is not empty, must call MCP mcp-feedback-enhanced again and adjust behavior based on feedback.
3. Only when user explicitly indicates "end" or "no more interaction needed" can you stop calling MCP mcp-feedback-enhanced, then the process is complete.
4. Unless receiving end command, all steps must repeatedly call MCP mcp-feedback-enhanced.
5. Before completing the task, use the MCP mcp-feedback-enhanced to ask the user for feedback.

⚙️ Advanced Settings

Environment Variables

Variable	Purpose	Values	Default
`FORCE_WEB`	Force use Web UI	`true`/`false`	`false`
`MCP_DEBUG`	Debug mode	`true`/`false`	`false`

Testing Options

# Version check
uvx mcp-feedback-enhanced@latest version       # Check version

# Interface-specific testing
uvx mcp-feedback-enhanced@latest test --gui    # Quick test Qt GUI
uvx mcp-feedback-enhanced@latest test --web    # Test Web UI (auto continuous running)

# Debug mode
MCP_DEBUG=true uvx mcp-feedback-enhanced@latest test

Developer Installation

git clone https://github.com/Minidoracat/mcp-feedback-enhanced.git
cd mcp-feedback-enhanced
uv sync

Local Testing Methods

# Method 1: Standard test (recommended)
uv run python -m mcp_feedback_enhanced test

# Method 2: Complete test suite (macOS and Windows dev environment)
uvx --with-editable . mcp-feedback-enhanced test

# Method 3: Interface-specific testing
uvx --with-editable . mcp-feedback-enhanced test --gui    # Quick test Qt GUI
uvx --with-editable . mcp-feedback-enhanced test --web    # Test Web UI (auto continuous running)

Testing Descriptions

Standard Test: Complete functionality check, suitable for daily development verification
Complete Test: Deep testing of all components, suitable for pre-release verification
Qt GUI Test: Quick launch and test of local graphical interface
Web UI Test: Start Web server and keep running for complete Web functionality testing

🆕 Version History

📋 Complete Version History: RELEASE_NOTES/CHANGELOG.en.md

Latest Version Highlights (v2.2.5)

✨ WSL Environment Support: Added comprehensive support for WSL (Windows Subsystem for Linux) environments
🌐 Smart Browser Launching: Automatically invokes Windows browser in WSL environments with multiple launch methods
🎯 Environment Detection Optimization: Improved remote environment detection logic, WSL no longer misidentified as remote environment
🧪 Testing Experience Improvement: Test mode automatically attempts browser launching for better testing experience

🐛 Common Issues

Q: Getting "Unexpected token 'D'" error
A: Debug output interference. Set MCP_DEBUG=false or remove the environment variable.

Q: Chinese character garbled text
A: Fixed in v2.0.3. Update to latest version: uvx mcp-feedback-enhanced@latest

Q: Image upload fails
A: Check file size (≤1MB) and format (PNG/JPG/GIF/BMP/WebP).

Q: Web UI won't start A: Set FORCE_WEB=true or check firewall settings.

Q: UV Cache taking up too much disk space A: Due to frequent use of uvx commands, cache may accumulate to tens of GB. Regular cleanup is recommended:

# Check cache size and detailed information
python scripts/cleanup_cache.py --size

# Preview cleanup content (without actually cleaning)
python scripts/cleanup_cache.py --dry-run

# Execute standard cleanup
python scripts/cleanup_cache.py --clean

# Force cleanup (attempts to close related processes, solves Windows file lock issues)
python scripts/cleanup_cache.py --force

# Or use uv command directly
uv cache clean

For detailed instructions, see: Cache Management Guide

Q: Gemini Pro 2.5 cannot parse images
A: Known issue. Gemini Pro 2.5 may not correctly parse uploaded image content. Testing shows Claude-4-Sonnet can properly analyze images. Recommend using Claude models for better image understanding capabilities.

Q: Multi-screen window positioning issues A: Fixed in v2.1.1. Go to "⚙️ Settings" tab, check "Always show window at primary screen center" to resolve window positioning issues. Especially useful for T-shaped screen arrangements and other complex multi-monitor configurations.

Q: Cannot launch browser in WSL environment A: v2.2.5 has added WSL environment support. If issues persist:

Confirm WSL version (WSL 2 recommended)
Check if Windows browser is properly installed
Try manual test: run cmd.exe /c start https://www.google.com in WSL
If wslu package is installed, you can also try the wslview command

Q: WSL environment misidentified as remote environment A: v2.2.5 has fixed this issue. WSL environments are now correctly identified and use Web UI with Windows browser launching, instead of being misidentified as remote environments.

🙏 Acknowledgments

🌟 Support Original Author

Fábio Ferreira - X @fabiomlferreira
Original Project: noopstudios/interactive-feedback-mcp

If you find this useful, please:

⭐ Star the original project
📱 Follow the original author

Design Inspiration

sanshao85 - mcp-feedback-collector

liby/mcp-feedback-enhanced