zivhdinfo/interactive-feedback-mcp-nodejs

开发工具

本页由 AI 翻译，技术细节请以原文为准。查看原文

28 stars 8 forks 质量 64 趋势 11NOASSERTION

Repository Install

Node.js 采用现代基于网页的用户界面实现交互反馈MCP

概览

- 英文规则集 - AI助手的全面使用规则- 越南规则集 - Quy tắc sử dụng toàn diện cho AI助手是 Fábio Ferreira 开发的交互式反馈 MCP（Python）的现代 Node.js 实现。该版本用响应式基于网页的界面取代了 Qt 桌面界面，提供了更好的用户体验和跨平台兼容性。由（@zivhdinfo）作为STMMO项目的一部分开发。为 Cursor、Cline 和 Windsurf 等 AI 开发工具创建一个“人工参与”的工作流程。该服务器允许您：- 运行命令并查看输出 - 直接向 AI 提供文本反馈 - 管理每个项目的配置 - 必要时自动执行命令通过引导助手与用户联系，而不是扩展到投机性、高成本的工具调用，该模块可以大幅减少像Cursor这样的平台上的高级请求（例如OpenAI工具调用）。

概述（AI 翻译）

互动反馈MCP - Phiên bản Node.js

🌍 语言 / Ngôn ngữ

英语
清越

📋 MCP 使用规则集 / Bộ quy tắc sử dụng MCP

英文规则集 - AI助手的全面使用规则
越南规则集 - Quy tắc sử dụng toàn diện cho AI 助理

英语

概述

交互式反馈MCP - Node.js实现是由Fábio Ferreira开发的现代互动反馈MCP（Python）的现代Node.js实现。该版本用响应式网页界面取代了Qt桌面界面，提供了更好的用户体验和跨平台兼容性。

由 Zivhd（@zivhdinfo）作为 STMMO 项目的一部分开发。

目的

为 Cursor、Cline 和 Windsurf 等 AI 开发工具创建一个“人工参与”工作流程。该服务器允许您：

运行命令并查看其输出
直接向人工智能提供文本反馈
管理每个项目的配置
必要时自动执行命令

为什么要用这个？

通过引导助手与用户联机，而不是扩展到投机性、高成本的工具调用，该模块可以大幅减少高级请求数量（例如：

本页由 AI 翻译，技术细节请以原文为准。

README

以下为原文 README 节选，完整内容请查看原文。

Interactive Feedback MCP - Node.js Implementation

Interactive Feedback MCP - Phiên bản Node.js

📋 MCP Usage Rulesets / Bộ quy tắc sử dụng MCP

English Ruleset - Comprehensive usage rules for AI assistants
Vietnamese Ruleset - Quy tắc sử dụng toàn diện cho AI assistants

English

Overview

Interactive Feedback MCP - Node.js Implementation is a modern Node.js implementation of the Interactive Feedback MCP (Python) developed by Fábio Ferreira. This version replaces the Qt desktop interface with a responsive web-based UI, providing better user experience and cross-platform compatibility.

Developed by Zivhd (@zivhdinfo) as part of the STMMO Project.

Purpose

Create a “human-in-the-loop” workflow for AI development tools like Cursor, Cline, and Windsurf. This server allows you to:

Run commands and view their output
Provide textual feedback directly to the AI
Manage per-project configurations
Auto-execute commands when needed

Why Use This?

By guiding the assistant to check in with the user instead of branching out into speculative, high-cost tool calls, this module can drastically reduce the number of premium requests (e.g., OpenAI tool invocations) on platforms like Cursor. In some cases, it helps consolidate what would be up to 25 tool calls into a single, feedback-aware request — saving resources and improving performance.

🌟 Features

✅ MCP Specification Compliant: 100% compatible with official MCP specification and JSON-RPC 2.0
🔄 Proper Handshake: Implements correct initialize/initialized handshake protocol
🛠️ Tool Management: Full support for tools/list and tools/call methods
🌐 Interactive Web UI: Modern, dark-themed interface with real-time feedback
🖥️ Cross-Platform: Works on Windows, macOS, and Linux
⚡ Real-Time Communication: WebSocket-based live updates
💻 Command Execution: Run and monitor system commands with live output
📁 Project Management: Per-project configuration and settings
📱 Responsive Design: Works on desktop and mobile devices

在 GitHub 查看完整 README

安装

This server does not publish a one-line install command.

Open the repository installation guide 新手？先看 mcpskill.org 教程 →

配置

{
  "mcpServers": {
    "interactive-feedback-mcp": {
      "command": "node",
      "args": [
        "C:\\path\\to\\interactive-feedback-mcp-nodejs\\server.js"
      ],
      "env": {
        "NODE_ENV": "production"
      }
    }
  }
}