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.
@gmh5225
基本信息
A native macOS MCP server for collecting interactive user feedback with AppleScript dialogs and image support.
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"interactive-feedback-macos-mcp": {
"command": "node",
"args": [
"/path/to/interactive-feedback-macos-mcp/src/mcp-server-macos.js"
]
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
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.
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.
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.
Node.js is required. The server relies on AppleScript, so it only works on macOS.
The README does not specify persistence; data is returned to the MCP client during the session.
The server runs as a child process via the `node` command (stdio transport). No authentication is mentioned.
`collect_feedback`, `pick_image`, `get_image_info`, and `take_screenshot`. These can be auto-approved in the Cursor MCP configuration.

Couples therapist Figs O'Sullivan (LMFT, 17 years, endorsed by Sue Johnson, creator of EFT) inside your AI. Ask relationship questions answered from his clinical writing, name the pattern in a fight, get a three-step rep
This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.

See and control a real Windows PC you own — from any MCP client, locally or remotely. Observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH: your machine, your key.

Request dedicated senior developers to work on your project, write job descriptions, and prep technical interviews — all without leaving your Claude chat. Just describe what you need, and Lemon.io MCP does the rest. 1–3
评论