Interactive Feedback MCP Server

一个强大的 [MCP 服务器](https://modelcontextprotocol.io/),在AI辅助开发工具如 [Cursor](https://www.cursor.com)

Local serverstdioPython

What is the Interactive Feedback MCP MCP server?

Interactive Feedback MCP becomes available to MCP clients through the interactive feedback mcp mcp server. 一个强大的 MCP 服务器,在AI辅助开发工具如 Cursor 中实现无缝的人机协作工作流程。该服务器允许您运行命令、查看输出结果,并通过直观的图形界面直接向AI提供丰富的文本反馈。.

What Interactive Feedback MCP does

一个强大的 MCP 服务器,在AI辅助开发工具如 Cursor 中实现无缝的人机协作工作流程。该服务器允许您运行命令、查看输出结果,并通过直观的图形界面直接向AI提供丰富的文本反馈。

Tools it exposes

Once connected, the assistant can call these 14 tools directly:

  • RIPER — 5协议集成** - (研究 → 创新 → 计划 → 执行 → 审查)
  • Windows — 注册表 HKEY_CURRENT_USER\Software\InteractiveFeedbackMCP\InteractiveFeedbackMCP
  • macOS — ~/Library/Preferences/com.InteractiveFeedbackMCP.InteractiveFeedbackMCP.plist
  • Linux — ~/.config/InteractiveFeedbackMCP/InteractiveFeedbackMCP.conf
  • run_command — 项目的默认执行命令
  • execute_automatically — 是否自动执行命令
  • suffix_mode — 反馈后缀模式(force/smart/none)
  • button_size — 按钮大小设置(small/medium/large/custom)
  • visible_buttons — 可见快捷按钮列表
  • language — 界面语言设置
  • use_base64_transmission — 是否启用Base64图片传输
  • base64_target_size_kb — Base64传输的目标文件大小
  • commandSectionVisible — 命令区域是否可见
  • quick_responses — 自定义快捷响应按钮配置

Installing the interactive feedback mcp mcp server

Setup follows the standard MCP pattern: clone or install the server, then register it in your client's configuration file and restart the client. The configuration snippets on this page cover Claude Desktop, Claude Code and Cursor.

Where it fits

Developer-tool servers are usually the first ones people connect, because they turn "help me with this code" into an assistant that can actually read the repo and act on it. Interactive Feedback MCP sits in that group, and the shape of its toolset — RIPER, Windows, macOS among others — tells you what it is really for. Worth comparing against the other developer tools servers in this directory before you commit to one, since several overlap in scope but differ sharply in setup cost and permissions.

Practical notes

  • This server runs locally, so it operates with whatever access your machine and its credentials already have. Scope that deliberately rather than by default.
  • With 14 tools exposed, expect a noticeable bump in prompt size — disable it in projects that never use Interactive Feedback MCP.
  • Maintained by liaosiqian, written in Python.
  • MCP clients ask for confirmation before each tool call by default. Keep that on while you learn what the interactive feedback mcp mcp server actually does with your data.
  • Every entry in this directory is reviewed by hand before it goes live, and details are checked against the project's own documentation.

Available tools

ToolWhat it does
RIPER5协议集成** - (研究 → 创新 → 计划 → 执行 → 审查)
Windows注册表 HKEY_CURRENT_USER\Software\InteractiveFeedbackMCP\InteractiveFeedbackMCP
macOS~/Library/Preferences/com.InteractiveFeedbackMCP.InteractiveFeedbackMCP.plist
Linux~/.config/InteractiveFeedbackMCP/InteractiveFeedbackMCP.conf
run_command项目的默认执行命令
execute_automatically是否自动执行命令
suffix_mode反馈后缀模式(force/smart/none)
button_size按钮大小设置(small/medium/large/custom)
visible_buttons可见快捷按钮列表
language界面语言设置
use_base64_transmission是否启用Base64图片传输
base64_target_size_kbBase64传输的目标文件大小
commandSectionVisible命令区域是否可见
quick_responses自定义快捷响应按钮配置

How to install the Interactive Feedback MCP MCP server

{
  "mcpServers": {
    "interactive-feedback-mcp": {
      "command": "uv",
      "args": [
        "--directory",
        "/path/to/interactive-feedback-mcp",
        "run",
        "server.py"
      ],
      "timeout": 600,
      "autoApprove": [
        "interactive_feedback"
      ]
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Example prompts to try

  • Use Interactive Feedback MCP to RIPER.
  • Use Interactive Feedback MCP to Windows.
  • Use Interactive Feedback MCP to macOS.

Frequently asked questions

It connects Interactive Feedback MCP to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (RIPER, Windows, macOS, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Interactive Feedback MCP directly.