Interactive Feedback MCP - 交互式反馈收集器

Name: Interactive Feedback MCP - 交互式反馈收集器
Author: bulice

@bulice

Repository

About Interactive Feedback MCP - 交互式反馈收集器

Interactive Feedback MCP Server - A tool for collecting user feedback with PySide6 interface

#interactive-feedback #feedback-collector #ai-assistant

Basic information

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "interactive-feedback-mcp": {
      "command": "uv",
      "args": [
        "sync"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Interactive Feedback MCP - 交互式反馈收集器?

Interactive Feedback MCP - 交互式反馈收集器 is an MCP (Model Context Protocol) server that provides a graphical user interface for human-in-the-loop feedback during AI-assisted development. It allows users to submit text feedback, upload images, execute commands, and see real-time output, enabling collaborative development with AI tools like Cursor, Cline, and Windsurf.

How to use Interactive Feedback MCP - 交互式反馈收集器?

Clone the repository, install dependencies with uv sync or pip install -r requirements.txt, then run uv run server.py or python server.py. Configure the server in your AI tool’s MCP settings (e.g., Cursor’s mcpServers JSON) with the path to mcp_server.sh. The AI assistant can call the interactive_feedback tool to prompt the user for input.

Key features of Interactive Feedback MCP - 交互式反馈收集器

Two-way text feedback with AI assistants via a GUI
Multi-image upload or clipboard paste support
Real-time command execution with live output and process monitoring
Dark and light theme switching with responsive design
Project-specific configuration persistence using Qt QSettings
Command history and auto-execute on startup option

Use cases of Interactive Feedback MCP - 交互式反馈收集器

Reducing speculative high-cost tool calls by confirming intent with the user before proceeding
Collecting detailed human feedback during iterative code generation or debugging sessions
Enabling visual feedback by attaching screenshots or diagrams to AI conversations
Running and reviewing command outputs interactively within the AI development workflow

FAQ from Interactive Feedback MCP - 交互式反馈收集器

What are the system requirements?

Python 3.11 or higher, and the server runs on Windows, macOS, and Linux. The recommended package manager is uv.

How do I configure the server for Cursor?

Add a JSON entry under mcpServers in Cursor’s MCP configuration, specifying the command as the full path to mcp_server.sh, with timeout 600 and autoApprove for interactive_feedback.

What tools does the MCP server expose?

It provides the interactive_feedback tool for text/image feedback and the get_image_info tool for image details.

Where are configuration settings stored?

Settings are stored per project using Qt’s QSettings in platform‑specific locations (e.g., Windows registry, macOS plist, Linux config files). This includes command to run, auto‑execute flag, window geometry, and UI state.