What Python version is required?
Python 3.10 or later is recommended.
@golf-mcp
Basic information
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
No standard config provided
This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.
RepositoryTool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
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).


Launch your product from your AI agent. Connect Claude Code, Codex, Cursor or ChatGPT to Launchdog over MCP and your agent drafts the listing, picks a launch week and books it. 50 launches a week, ranked only by human vo

Agent-Native Terminal

Eased is a library of motion-first React components for shadcn, installed with the shadcn CLI.
Gives AI agents public URLs (tunnels) for localhost, live HTTP traffic inspection, snapshot publishing, and access control. Part of LocalCan, the ngrok alternative for Mac, Windows and Linux. Free plan.
Comments