skillmcp

Turn any folder of agent skills into a live MCP server with one zero-dependency command.

🎯 Why?

Trending repos show fast-growing agent-skill ecosystems and MCP-powered coding agents, but skills are usually static SKILL.md or JSON folders without a universal local bridge. Existing MCP servers are app-specific or require heavy SDK setup. skillmcp fills the gap with a tiny stdio MCP adapter that discovers, validates, searches, and exposes skill files to Claude, Cursor, or any MCP client.

Target audience: AI agent developers, Claude Code/Cursor users, platform teams, and open-source skill authors who want reusable skills exposed to MCP clients without writing a custom server.

Related MCP server: SkillForge MCP

✨ Features

• ✨ *Recursively discovers SKILL.md, .skill.md, and skill.json skill files

• ✨ Exposes skills_list, skills_get, and skills_search as MCP tools

• ✨ Validates skill folders from the CLI with human or JSON output

• ✨ Runs as a dependency-free stdio MCP server with resources/read support

🚀 Quick Start

# Install
pip install skillmcp

# Run
skillmcp --help

📦 Installation

From Source

git clone https://github.com/YOUR_USERNAME/skillmcp.git
cd skillmcp

# Create virtual environment
python -m venv .venv
source .venv/bin/activate  # Windows: .venv\Scripts\activate

# Install in development mode
pip install -e ".[dev]"

# Run tests
pytest -v

🎬 Demo

The GIF above was recorded using Charm VHS:

vhs < demo.tape

📖 Usage

# Show help
skillmcp --help

# Common usage examples
skillmcp --example

🏗️ Architecture

graph LR
    A[Input] --> B[Core Engine]
    B --> C[Output]
    B --> D[Plugins]
    D --> E[Extensions]

🤝 Contributing

Contributions are welcome! Please:

1. Fork the repo

2. Create a feature branch (git checkout -b feature/amazing-feature)

3. Commit your changes (git commit -m 'Add amazing feature')

4. Push to the branch (git push origin feature/amazing-feature)

5. Open a Pull Request

📄 License

MIT © 2026 — See LICENSE for details.

If this project helped you, please ⭐ star it!

Made with ❤️ and AI