MCP.so
ログイン

Interactive Feedback MCP for macOS

@gmh5225

Interactive Feedback MCP for macOS について

A native macOS MCP server for collecting interactive user feedback with AppleScript dialogs and image support.

基本情報

カテゴリ

その他

ライセンス

MIT license

ランタイム

node

トランスポート

stdio

公開者

gmh5225

設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "interactive-feedback-macos-mcp": {
      "command": "node",
      "args": [
        "/path/to/interactive-feedback-macos-mcp/src/mcp-server-macos.js"
      ]
    }
  }
}

ツール

ツールは検出されませんでした

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is Interactive Feedback MCP for macOS?

A native macOS MCP server that uses AppleScript dialogs to collect interactive user feedback with optional image attachments. It provides tools for image picking, screenshot capture, and feedback gathering—all without a web server.

How to use Interactive Feedback MCP for macOS?

Clone the repository, run npm install, then add the server to your Cursor MCP configuration using the node command pointing to the mcp-server-macos.js file. In AI prompts, instruct the assistant to call collect_feedback to ask questions or end tasks.

Key features of Interactive Feedback MCP for macOS

  • Native macOS dialog windows via AppleScript
  • Built-in image picker and screenshot capture
  • No web server dependencies (Express, CORS, etc.)
  • Seamless integration with macOS user experience
  • Four tools: collect_feedback, pick_image, get_image_info, take_screenshot

Use cases of Interactive Feedback MCP for macOS

  • AI assistants asking users for confirmation or additional input using native dialogs
  • Collecting feedback with an attached image (e.g., screenshot or file)
  • Letting users pick an image file from the macOS file picker
  • Capturing area or full-screen screenshots from within an MCP context
  • Retrieving image metadata and base64 content for processing

FAQ from Interactive Feedback MCP for macOS

How is this different from the original interactive-feedback-mcp?

This version uses AppleScript dialogs instead of a web UI, adds built-in image picker and screenshot capture, and is more lightweight by removing web server dependencies.

What are the runtime requirements?

Node.js is required. The server relies on AppleScript, so it only works on macOS.

Where does feedback or image data live?

The README does not specify persistence; data is returned to the MCP client during the session.

How is the server transported and authenticated?

The server runs as a child process via the node command (stdio transport). No authentication is mentioned.

Which tools are available?

collect_feedback, pick_image, get_image_info, and take_screenshot. These can be auto-approved in the Cursor MCP configuration.

コメント

「その他」の他のコンテンツ