What is Homebrew MCP Python Server and what does it do?
It is an MCP server that turns Homebrew commands (install, search, doctor, etc.) into tools that MCP client applications like Claude Desktop can call directly.
@jeannier
基本情報
Homebrew MCP : Comprehensive brew support for installing, upgrading, searching, and maintaining macOS packages.
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": {
"homebrew-mcp": {
"command": "uv",
"args": [
"venv"
]
}
}
}ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
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。
A Model Context Protocol (MCP) server for Homebrew package management on macOS, designed for integration with Claude Desktop and other MCP-compatible clients. It exposes Homebrew commands as MCP tools for use by LLM clients.
Install via cloning the repo, setting up a uv-managed Python virtual environment, and installing dependencies. For Claude Desktop, configure ~/Library/Application Support/Claude/claude_desktop.json with a uv run command pointing to the project. For Cursor, use the provided "Add to Cursor" button or manually edit ~/.cursor/mcp.json. The server runs via stdio and logs to homebrew_mcp.log.
brew commands via subprocess on macOShomebrew_mcp.logbrew doctorIt is an MCP server that turns Homebrew commands (install, search, doctor, etc.) into tools that MCP client applications like Claude Desktop can call directly.
Requires macOS, Homebrew installed, Python 3.13, and the `uv` dependency manager. The MCP Python SDK and Anthropic SDK (for the test script) are installed via `requirements.txt`.
Logs are written to `homebrew_mcp.log` in the project directory. The server runs real `brew` commands, so package data resides in the normal Homebrew locations. The virtual environment is in `.venv`.
It uses stdio transport (MCP spec 2025-06-18) with JSON-RPC 2.0 messaging. No authentication is built-in; it relies on local machine access.
Yes, it is designed for any MCP-compatible client. The README includes specific integration instructions for Cursor and demonstrates interaction with Claude via the Anthropic API test script.
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.

Model Context Protocol Servers
不止于 CSS

Connect your AI assistant to your own YOUB endurance training account. Read recorded activities with full analysis, planned sessions, race goals, wellness (HRV, sleep, resting HR) and your athletic profile. Create or mov
コメント