Mcp Feedback Enhanced
About
# MCP Feedback Enhanced **🌐 Language / 語言切換:** **English** | [繁體中文](README.zh-TW.md) | [简体中文](README.zh-CN.md) **Original Author:** [Fábio Ferreira](https://x.com/fabiomlferreira) | [Original Project](https://github.com/noopstudios/interactive-feedback-mcp) ⭐ **Enhanced Fork:**…
Details
- Author
- Minidoracat
- Downloads
- 324
- Categories
- Developer Tools, Automation, AI, Productivity, Other
Jump to
Desktop Application - Native cross-platform desktop application based on Tauri framework, supporting Windows, macOS, Linux with exactly the same functionality as Web UI
- Ctrl+Enter（Windows/Linux）/Cmd+Enter（macOS）：Submit feedback (both main keyboard and numeric keypad supported)
- Ctrl+V（Windows/Linux）/Cmd+V（macOS）：Direct paste clipboard images
- Ctrl+I（Windows/Linux）/Cmd+I（macOS）：Quick focus input box (Thanks @penn201500)
# Install uv (if not already installed) pip install uv
Basic Configuration(suitable for most users):
{ "mcpServers": { "mcp-feedback-enhanced": { "command": "uvx", "args": ](https://www.trae.ai)["mcp-feedback-enhanced@latest"], "timeout": 600, "autoApprove": ["interactive_feedback"] } } }
Advanced Configuration(requires custom environment):
{ "mcpServers": { "mcp-feedback-enhanced": { "command": "uvx", "args": ["mcp-feedback-enhanced@latest"], "timeout": 600, "env": { "MCP_DEBUG": "false", "MCP_WEB_HOST": "127.0.0.1", "MCP_WEB_PORT": "8765", "MCP_LANGUAGE": "en" }, "autoApprove": ["interactive_feedback"] } } }
Desktop Application Configuration(v2.5.0 new feature - using native desktop application):
{ "mcpServers": { "mcp-feedback-enhanced": { "command": "uvx", "args": ["mcp-feedback-enhanced@latest"], "timeout": 600, "env": { "MCP_DESKTOP_MODE": "true", "MCP_WEB_HOST": "127.0.0.1", "MCP_WEB_PORT": "8765", "MCP_DEBUG": "false" }, "autoApprove": ["interactive_feedback"] } } }
- Desktop Mode:examples/mcp-config-desktop.json
- Web Mode:examples/mcp-config-web.json
For optimal results, add the following rules to your AI assistant:
# MCP Interactive Feedback Rules follow mcp-feedback-enhanced instructions
- 127.0.0.1(default): Local access only, higher security
- 0.0.0.0: Allow remote access, suitable for SSH remote development environments
- Used to force the interface language, overriding automatic system detection
- Supported language codes:
- zh-TW: Traditional Chinese
- zh-CN: Simplified Chinese
- en: English
- User-saved language settings in the interface (highest priority)
- MCP_LANGUAGEenvironment variable
- System environment variables (LANG, LC_ALL, etc.)
- System default language
- Fallback to default language (Traditional Chinese)
# Version check uvx mcp-feedback-enhanced@latest version # Check version # Interface testing uvx mcp-feedback-enhanced@latest test --web # Test Web UI (auto continuous running) uvx mcp-feedback-enhanced@latest test --desktop # Test desktop application (v2.5.0 new feature) # Debug mode MCP_DEBUG=true uvx mcp-feedback-enhanced@latest test # Specify language for testing MCP_LANGUAGE=en uvx mcp-feedback-enhanced@latest test --web # Force English interface MCP_LANGUAGE=zh-TW uvx mcp-feedback-enhanced@latest test --web # Force Traditional Chinese MCP_LANGUAGE=zh-CN uvx mcp-feedback-enhanced@latest test --web # Force Simplified Chinese
git clone https://github.com/Minidoracat/mcp-feedback-enhanced.git cd mcp-feedback-enhanced uv sync
# Functional testing make test-func # Standard functional testing make test-web # Web UI testing (continuous running) make test-desktop-func # Desktop application functional testing # Or use direct commands uv run python -m mcp_feedback_enhanced test # Standard functional testing uvx --no-cache --with-editable . mcp-feedback-enhanced test --web # Web UI testing (continuous running) uvx --no-cache --with-editable . mcp-feedback-enhanced test --desktop # Desktop application testing # Desktop application build (v2.5.0 new feature) make build-desktop # Build desktop application (debug mode) make build-desktop-release # Build desktop application (release mode) make test-desktop # Test desktop application make clean-desktop # Clean desktop build artifacts # Unit testing make test # Run all unit tests make test-fast # Fast testing (skip slow tests) make test-cov # Test and generate coverage report # Code quality checks make check # Complete code quality check make quick-check # Quick check and auto-fix
- Functional Testing: Test complete MCP tool functionality workflow
- Unit Testing: Test individual module functionality
- Coverage Testing: Generate HTML coverage report tohtmlcov/directory
- Quality Checks: Include linting, formatting, type checking
📋Complete Version History:RELEASE_NOTES/CHANGELOG.en.md
- 🚀Auto Command Execution: Automatically execute preset commands after creating new sessions or commits, improving workflow efficiency
- 📊Session Export Feature: Support exporting session records to multiple formats for easy sharing and archiving
- ⏸️Auto-commit Control: Added pause and resume buttons for better control over auto-commit timing
- 🔔System Notifications: System-level notifications for important events with real-time alerts
- ⏱️Session Timeout Optimization: Redesigned session management with more flexible configuration options
- 🌏I18n Enhancement: Refactored internationalization architecture with full multilingual support for notifications
- 🎨UI Simplification: Significantly simplified user interface for improved user experience
Q: Browser cannot launch or access in SSH Remote environmentA: Two solutions available:
Solution 1: Environment Variable Setting (v2.5.5 Recommended)Set"MCP_WEB_HOST": "0.0.0.0"in MCP configuration to allow remote access:
{ "mcpServers": { "mcp-feedback-enhanced": { "command": "uvx", "args": ["mcp-feedback-enhanced@latest"], "timeout": 600, "env": { "MCP_WEB_HOST": "0.0.0.0", "MCP_WEB_PORT": "8765" }, "autoApprove": ["interactive_feedback"] } } }
Then open in local browser:http://[remote-host-IP]:8765
Solution 2: SSH Port Forwarding (Traditional Method)
- Use default configuration (MCP_WEB_HOST:127.0.0.1)
- Set up SSH port forwarding:
- VS Code Remote SSH: PressCtrl+Shift+P→ "Forward a Port" → Enter8765
- Cursor SSH Remote: Manually add port forwarding rule (port 8765)
For detailed solutions, refer to:SSH Remote Environment Usage Guide
Q: Why am I not receiving new MCP feedback?A: Likely a WebSocket connection issue.Solution: Directly refresh the browser page.
Q: Why isn't MCP being called?A: Please confirm MCP tool status shows green light.Solution: Repeatedly toggle MCP tool on/off, wait a few seconds for system reconnection.
Q: Augment cannot start MCPA:Solution: Completely close and restart VS Code or Cursor, reopen the project.
Q: How to use desktop application?A: v2.5.0 introduces cross-platform desktop application support. Set"MCP_DESKTOP_MODE": "true"in MCP configuration to enable:
{ "mcpServers": { "mcp-feedback-enhanced": { "command": "uvx", "args": ["mcp-feedback-enhanced@latest"], "timeout": 600, "env": { "MCP_DESKTOP_MODE": "true", "MCP_WEB_PORT": "8765" }, "autoApprove": ["interactive_feedback"] } } }
Configuration File Example:examples/mcp-config-desktop.json
Q: How to use legacy PyQt6 GUI interface?A: v2.4.0 completely removed PyQt6 GUI dependencies. To use legacy GUI, specify v2.3.0 or earlier:uvx mcp-feedback-enhanced@2.3.0Note: Legacy versions don't include new features (prompt management, auto-submit, session management, desktop application, etc.).
Q: "Unexpected token 'D'" error appearsA: Debug output interference. SetMCP_DEBUG=falseor remove the environment variable.
Q: Chinese character garbled textA: Fixed in v2.0.3. Update to latest version:uvx mcp-feedback-enhanced@latest
Q: Window disappears or positioning errors in multi-screen environmentA: 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.
Q: Image upload failureA: Check file format (PNG/JPG/JPEG/GIF/BMP/WebP). System supports any size image files.
Q: Web UI cannot startA: Check firewall settings or try using different ports.
Q: UV Cache occupies too much disk spaceA: Due to frequent use ofuvxcommands, cache may accumulate to tens of GB. Regular cleanup recommended:
# View cache size and detailed information python scripts/cleanup_cache.py --size # Preview cleanup content (no actual cleanup) python scripts/cleanup_cache.py --dry-run # Execute standard cleanup python scripts/cleanup_cache.py --clean # Force cleanup (attempts to close related programs, solving Windows file occupation issues) python scripts/cleanup_cache.py --force # Or directly use uv command uv cache clean
For detailed instructions, refer to:Cache Management Guide
Q: AI models cannot parse imagesA: 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:
- Ensure good image quality (high contrast, clear text)
- Try uploading multiple times, retries usually succeed
- If parsing continues to fail, try adjusting image size or format
Fábio Ferreira-X @fabiomlferreiraOriginal Project:noopstudios/interactive-feedback-mcp
- ⭐Star the original project
- 📱Follow the original author
- 🎯 Auto-focus input box feature (PR #39)
- 🌐 SSH Remote Development Support (MCP_WEB_HOSTenvironment variable) (PR #113)
- 🍎 macOS PyO3 Compilation Configuration Support (PR #93)
- 📝 Tool Documentation Optimization (LLM instructions moved to docstring) (PR #105)
- Discord:https://discord.gg/Gur2V67
- Issues:GitHub Issues
MIT License - SeeLICENSEfile for details
🌟 Welcome to Star and share with more developers!
This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.
Desktop MCP server manager for 14 AI clients. Browse and install 9,200+ MCP servers and 3,100+ AI Skills across Cursor, VS Code, Claude Code, Gemini CLI, and more from one GUI.
200+ production tools for AI agents via Remote MCP. GitHub, Slack, Notion, Linear, Figma, Stripe, web search, OCR, document conversion, semantic memory/recall, Finviz, SEC filings, image generation, and more.
What Shopify did for ecommerce, Chipp does for AI agents. Build, deploy, and monetize AI agents for your business — no engineering team required.
CodeVF MCP lets AI hand off problems to real engineers instantly, so your workflows don’t stall when models hit their limits.
Client implementation for Mastra, providing seamless integration with MCP-compatible AI models and tools.
Agent-native developer Q&A API with MCP + A2A endpoints for citations, job pickup, and answer submission.
On-demand access to 150+ specialist AI agent templates — search, browse, and spawn agents. 150x reduction in context usage vs loading agents locally.
AgentChatBus is a persistent AI communication bus that lets multiple independent AI Agents chat, collaborate, and delegate tasks — across terminals, across IDEs, and across frameworks.
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Mcp Feedback EnhancedCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Install Python package uv then configure your MCP client with JSON using the command uvx mcp-feedback-enhanced@latest. Set environment variables like MCP_DESKTOP_MODE or MCP_WEB_HOST as needed. Add the prompt “follow mcp-feedback-enhanced instructions” to your AI assistant for best results. Test with uvx mcp-feedback-enhanced@latest test --web or --desktop.
interactive_feedback
Interactive feedback collection tool for LLM agents. USAGE RULES: 1. During any process, task, or conversation, whether asking, replying, or completing phased tasks, you must call this tool to ask for feedback. 2. Unless receiving termination instructions, all steps must repeatedly call this tool. 3. Whenever user feedback is received, if the feedback content is not empty, you must call this tool again and adjust behavior based on the feedback content. 4. Only when the user explicitly indicates "end" or "no more interaction needed" can you stop calling this tool, and the process is considered complete. 5. You should summarize what have done, and provide project directory through args to let user know what you have done to provide feedback for next step. Args: project_directory: Project directory path for context summary: Summary of AI work completed for user review timeout: Timeout in seconds for waiting user feedback (default: 600 seconds) Returns: list: List containing TextContent and MCPImage objects representing user feedback
get_system_info
獲取系統環境資訊 Returns: str: JSON 格式的系統資訊
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"mcp feedback enhanced": {
"mcp-feedback-enhanced": {
"command": "uvx",
"args": [
"mcp-feedback-enhanced@latest"
],
"timeout": 600,
"autoApprove": [
"interactive_feedback"
]
}
}
}
}McpServers
{
"mcp-feedback-enhanced": {
"command": "uvx",
"args": [
"mcp-feedback-enhanced@latest"
],
"timeout": 600,
"autoApprove": [
"interactive_feedback"
]
}
}Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
