Marketplace for trusted AI agent skills

Skill Detail

Build authenticated MCP servers from Python files with Golf

Scaffold, build, and run MCP servers from a predictable Python project layout with tools, prompts, resources, auth, and OpenTelemetry hooks.

Integrations & ConnectorsMCP
Integrations & Connectors MCP Security Reviewed
⭐ 835 GitHub stars
COPY SKILL INSTRUCTIONS (OPTIONAL)
npx skills add agentskillexchange/skills --skill build-authenticated-mcp-servers-from-python-files-with-golf Copy
Uses the third-party skills CLI, not an ASE-owned installer. Check your agent’s compatibility. This copies instructions; complete the upstream tool setup below separately.
View source Documentation
At a glance
Tools required
Python 3.10+, pip, Golf CLI, MCP-compatible client
Install & setup
Install with pip install golf-mcp, create a project with golf init your-project-name, then run golf build dev and golf run after reviewing golf.json, auth.py, and generated tools/resources/prompts.
Author
golf-mcp
Publisher
Open Source
Last updated
Jul 6, 2026
Quick brief

Use Golf when an agent or operator needs to turn a small set of Python tool, prompt, and resource files into a runnable MCP server without hand-building the server boilerplate. The workflow is to install the PyPI package, run `golf init`, add or review files under `tools/`, `resources/`, and `prompts/`, configure transport, auth, and telemetry in `golf.json` and `auth.py`, then build and run the server for an MCP-compatible client. Invoke this instead of using the product normally when the job is repeatable MCP server creation with explicit schemas, authentication, and observability around agent tools, not a one-off script or generic Python service. The boundary is Python MCP server scaffolding, component discovery, auth configuration, and runtime operation; it is not a broad MCP platform, dashboard, or generic framework listing.

How it works

What this skill actually does

Inputs and prerequisites: Python 3.10 or newer, pip, Golf project files, and an MCP-compatible client for integration testing.

Setup notes: Install with `pip install golf-mcp`, initialize a project with `golf init your-project-name`, then run `golf build dev` and `golf run`. Configure JWT, OAuth server, API key, or development-token auth in `auth.py`; enable OpenTelemetry through the documented environment variables when traces are needed.

Source and verification boundary: use https://docs.golf.dev and https://github.com/golf-mcp/golf as the canonical references before running the workflow; keep generated tools, auth settings, telemetry choices, and MCP client exposure reviewable against that upstream source.

Framework fit: publish this as an MCP workflow because Golf’s central invocation is building and running MCP servers for MCP-compatible clients.