What Python version is required?
Python 3.10 or later is recommended.
@golf-mcp
基本情報
Production-Ready MCP Server Framework • Build, deploy & scale secure AI agent infrastructure • Includes Auth, Observability, Debugger, Telemetry & Runtime • Run real-world MCPs powering AI Agents
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。
Golf is a framework for building MCP (Model Context Protocol) servers. It allows developers to define server capabilities—tools, prompts, and resources—as simple Python files within a conventional directory structure, then automatically discovers and compiles them into a runnable MCP server. Golf is designed for Python developers who want to create MCP servers with minimal boilerplate, and includes built-in authentication, utilities for LLM interactions, and automatic telemetry.
Install Golf with pip install golf-mcp (Python 3.10+ required). Initialize a project using golf init your-project-name. Run the development server with golf build dev && golf run. Components are defined in tools/, resources/, and prompts/ directories; each Python file defines one component, with its module docstring serving as the description. Authentication is configured in an auth.py file using the configure_auth function.
golf init and golf run.Python 3.10 or later is recommended.
Install it using pip: `pip install golf-mcp`.
Golf supports JWT, OAuth Server mode, API key (static tokens), and development tokens. Authentication is configured in an `auth.py` file using the `configure_auth` function.
Yes. Run `golf telemetry disable` to permanently disable anonymous usage data collection. You can also use `--no-telemetry` with any command, or re-enable telemetry with `golf telemetry enable`.
Component IDs are automatically derived from the file path. For example, `tools/hello.py` becomes `hello`, and `tools/payments/submit.py` becomes `submit_payments` (filename followed by reversed parent directories under the main category, joined by underscores).

Verified distributed compute for humans, applications, and agents. Submit Blender, Octane, and video workloads, route them across qualified GPUs, track asynchronous execution, download finished artifacts, and verify FARP

Nebelus is an enterprise agentic-AI platform for regulated industries. This MCP server exposes the Nebelus Construction API: ~48 tools that give an MCP client full agent build parity — create/update/probe agents, edit ag
Open-source MCP server for Google Play developer workflows. Runs locally with your own credentials.

Local-first credential broker for MCP. AI coding agents (Claude Code, Cursor, Codex…) call APIs, SSH and databases through scoped presets; secrets stay in your OS keychain and never enter the agent's context.

Catch intent conflicts before code conflicts. The open-source coordination protocol for coding agents, built above Git.
コメント