zivhdinfo/interactive-feedback-mcp-nodejs

Developer tools

このページは AI により自動翻訳されています。技術的な詳細は原文をご確認ください。原文を見る

28 stars 8 forks 品質 64 トレンド 11NOASSERTION

Repository Install

Node.js implementation of Interactive Feedback MCP with modern web-based UI

概要

- English Ruleset - Comprehensive usage rules for AI assistants - Vietnamese Ruleset - Quy tắc sử dụng toàn diện cho AI assistants 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 (@zivhdinfo) as part of the STMMO Project. 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 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.

README

以下は原文 README の抜粋です。原文を見る。

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

GitHub で README 全文を見る

インストール

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

Open the repository installation guide MCP 初心者？mcpskill.org のガイドから始めましょう →

設定

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