Skills MCP

# Skills MCP [](https://pypi.org/project/skills-mcp/) [](LICENSE) [](https://pypi.org/project/skills-mcp/) The **Package Manager for AI Agents**. Skills MCP connects your LLM Agent (like Claude Desktop or Claude Code) to a global registry of capabilities. It allows your Agent to autonomously discover, install, and learn new skills to solve complex tasks. > **Thin MCP, Fat Agent Philosophy:** This tool handles the delivery of code and instructions, empowering the Agent to execute them using its own environment (e.g., `uv`, `bash`). --- ## 🚀 Features - **Search:** Find skills for specific tasks (e.g., "pdf", "excel", "diagram"). - **Install:** One-click download and installation to your local machine (`~/.skills`). - **Learn:** Provides the Agent with the exact file structure and `SKILL.md` instructions. - **Dependency Management:** Works seamlessly with `uv` to let Agents self-manage Python environments without polluting your system. --- ## 📦 Installation The recommended way to install is via `uv` (a fast Python package manager). It ensures the tool runs in an isolated environment. ### Prerequisites - Python 3.10+ - `uv` (Recommended) ```bash # 1. Install uv (if you haven't already) curl -LsSf https://astral.sh/uv/install.sh | sh # 2. Install Skills MCP globally uv tool install skills-mcp ``` *(Alternatively, you can use `pip`, but we strongly recommend `uv` to avoid dependency conflicts.)* --- ## ⚙️ Configuration ### 🖥️ Claude Desktop (GUI) To use Skills MCP with the Claude Desktop app, update your configuration file: - **macOS:** `~/Library/Application Support/Claude/claude_desktop_config.json` - **Windows:** `%APPDATA%\Claude\claude_desktop_config.json` Add the following entry: ```json { "mcpServers": { "skills": { "command": "uv", "args": ["tool", "run", "skills-mcp"], "env": { "SKILLS_ROOT": "/Users/YOUR_USERNAME/.skills", "SKILLS_REGISTRY_URL": "https://skills.leezhu.cn/api/v1" } } } } ``` *Tip: Replace `/Users/YOUR_USERNAME` with your actual home directory path.* ### ⌨️ Claude Code (CLI) If you are using the `claude` command-line tool, you can install the MCP server directly via the CLI: ```bash # Add the MCP server claude mcp add skills -- uv tool run skills-mcp ``` **Note on Configuration:** Claude Code inherits environment variables from your shell. To set custom configurations (like a private registry URL), export them in your shell profile (`~/.zshrc` or `~/.bashrc`): ```bash export SKILLS_REGISTRY_URL="https://your-private-registry.com/api/v1" ``` ### Environment Variables | Variable | Description | Default | | :--- | :--- | :--- | | `SKILLS_ROOT` | Where skills are installed locally. | `~/.skills` | | `SKILLS_REGISTRY_URL` | The API endpoint of the skills registry. | `https://skills.leezhu.cn/api/v1` | | `SKILLS_API_KEY` | (Optional) Token for private registries. | `None` | --- ## 💡 Usage Guide (for Agents) Once installed, you can ask Claude to do things like: 1. **Discovery:** > "Search for a skill that can split Excel files." *(Claude calls `skills_search`)* 2. **Acquisition:** > "Install the excel-pro skill." *(Claude calls `skills_install`)* 3. **Execution:** > "Read the instructions for excel-pro and split this file." *(Claude calls `skills_get_details`, reads the `SKILL.md`, installs dependencies via `uv`, and runs the script)* --- ## 🛠️ Development ### Setup ```bash git clone https://github.com/leezhuuuuu/skills-mcp.git cd skills-mcp # Install dependencies uv sync ``` ### Running Locally (StdIO Mode) ```bash # Direct run uv run skills-mcp ``` --- ## 🤝 Contributing We welcome contributions! Please feel free to submit a Pull Request. 1. Fork the repository. 2. Create your feature branch. 3. Commit your changes. 4. Push to the branch. 5. Open a Pull Request. ## 📄 License This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.