npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

@embrs/user-feedback

v1.3.6

Published

基於 Node.js 的 MCP 反饋收集器 - 支援 AI 工作彙報和用戶反饋收集

Readme

User Feedback

npm version

基於 Node.js 的 MCP 反饋收集工具,支援 AI 工作彙報和用戶反饋收集。

功能特點

  • MCP 協議支援:符合 Model Context Protocol 標準,可與 Claude Desktop、Cursor 等 MCP 客戶端整合
  • 左右分割介面:左側顯示 AI 工作彙報,右側為用戶反饋區域
  • 圖片處理:支援拖放上傳、順序調整、彈窗檢視
  • 罐頭語快速回覆:預設常用回覆,支援自訂編輯
  • 深色主題:與 IDE 環境風格一致

系統需求

  • Node.js 18.0.0 或更高版本
  • npm 或 yarn 套件管理器

安裝

📦 npm 套件: https://www.npmjs.com/package/@embrs/user-feedback

# 全域安裝
npm install -g @embrs/user-feedback

# 更新到最新版本
npm update -g @embrs/user-feedback

# 或使用 npx 直接執行(無需安裝,自動使用最新版)
npx @embrs/user-feedback@latest --help

解除安裝

npm uninstall -g @embrs/user-feedback

注意:解除安裝後,請記得從 MCP 客戶端配置中移除相關設定。

使用方式

作為 MCP 服務器

# 啟動 MCP 服務器(預設模式)
user-feedback start

# 指定端口
user-feedback start --port 3000

# 啟用除錯模式
user-feedback start --debug

僅 Web 模式(測試用)

user-feedback start --web

其他命令

# 檢查配置和系統狀態
user-feedback health

# 顯示當前配置
user-feedback config

MCP 客戶端配置

Cursor

  1. 打開 Cursor 設定(Cmd + ,
  2. 搜尋 "MCP" 或進入 Features → MCP Servers
  3. 點擊 "Edit in settings.json" 或 "Add Server"
  4. 添加以下配置:
{
  "mcpServers": {
    "user-feedback": {
      "command": "npx",
      "args": ["-y", "@embrs/user-feedback"],
      "env": {
        "MCP_WEB_PORT": "3000",
        "MCP_DIALOG_TIMEOUT": "60000",
        "LOG_LEVEL": "warn"
      }
    }
  }
}
  1. 重啟 Cursor 使配置生效

💡 提示:可以在 env 中設定任何環境變數,優先順序高於 .env 文件。

Claude Desktop

~/Library/Application Support/Claude/claude_desktop_config.json 中添加:

{
  "mcpServers": {
    "user-feedback": {
      "command": "npx",
      "args": ["-y", "@embrs/user-feedback"],
      "env": {
        "MCP_WEB_PORT": "3000",
        "MCP_DIALOG_TIMEOUT": "60000",
        "LOG_LEVEL": "warn"
      }
    }
  }
}

Windsurf

在 MCP 設定中添加:

{
  "mcpServers": {
    "user-feedback": {
      "command": "npx",
      "args": ["-y", "@embrs/user-feedback"],
      "env": {
        "MCP_WEB_PORT": "3000",
        "MCP_DIALOG_TIMEOUT": "60000",
        "LOG_LEVEL": "warn"
      }
    }
  }
}

環境變數配置

🎯 推薦方式:MCP 客戶端配置

直接在 MCP 客戶端配置中設定環境變數,優先順序最高:

{
  "mcpServers": {
    "user-feedback": {
      "command": "npx",
      "args": ["-y", "@embrs/user-feedback"],
      "env": {
        "MCP_WEB_PORT": "3000",
        "MCP_DIALOG_TIMEOUT": "60000",
        "LOG_LEVEL": "warn"
      }
    }
  }
}

📁 備用方式:.env 文件

複製 .env.example.env 並根據需要修改:

| 變數 | 說明 | 預設值 | |------|------|--------| | MCP_WEB_PORT | Web 服務器端口 | 3239 | | MCP_DIALOG_TIMEOUT | 反饋超時時間(秒) | 60000 | | LOG_LEVEL | 日誌級別(silent/error/warn/info/debug) | info | | MCP_MAX_FILE_SIZE | 最大檔案大小(位元組) | 10485760 (10MB) |

MCP 工具 API

collect_feedback

收集用戶對 AI 工作的反饋。

參數:

  • work_summary (string, 必填):AI 工作彙報內容

返回:

  • 用戶提交的反饋內容(文字和/或圖片)

範例:

AI 調用 collect_feedback 工具,傳入工作彙報內容
→ 系統開啟 Web 介面
→ 用戶在介面中提交反饋
→ 反饋內容返回給 AI

開發

詳見 DEV.md

授權

MIT License