sktime-mcp

# sktime-mcp **[Read the Documentation](http://sktime.github.io/sktime-mcp/)** | **[PyPI Package](https://pypi.org/project/sktime-mcp/0.1.0/)** **MCP (Model Context Protocol) layer for sktime - Registry-Driven for LLMs** A semantic engine that exposes sktime's native registry and semantics to Large Language Models, enabling them to: - 🔍 **Discover** valid estimators - 🧠 **Reason** about estimator capabilities - 🔗 **Compose** compatible estimators - ⚡ **Execute** real sktime workflows on real data ## 🎯 Design Philosophy This MCP is **not** just documentation or static code analysis. It is a **semantic engine** for programmatic model usage. ### Key Principles 1. **sktime as Source of Truth** - No AST parsing, no repo indexing, no heuristics. All structure comes from `all_estimators`, estimator tags, and sktime's API contracts. 2. **Registry-First** - Instead of `File → Class → Infer Relationships`, we do `Registry → Semantics → Safe Execution`. 3. **Minimal MCP Surface** - Exposes only what an LLM needs: Discovery, Description, Instantiation, Execution, and model persistence. ## 🛠️ Installation ### Zero-install via uvx (recommended) If you have [uv](https://github.com/astral-sh/uv) installed, no separate installation step is needed. Just update your MCP client config (see [Connecting from an LLM Client](#connecting-from-an-llm-client) below) and `uvx` will handle the rest automatically. ```bash # Verify uv is available uvx sktime-mcp --help ``` ### pip ```bash pip install sktime-mcp # With optional extras (SQL, forecasting models, file formats) pip install "sktime-mcp[all]" ``` ### Development installation ```bash git clone https://github.com/sktime/sktime-mcp cd sktime-mcp python3 -m pip install -e ".[dev]" ``` ### 🐳 Docker Run without installing anything locally (only Docker required): ```bash # Build the image docker build -t sktime-mcp . # Run the MCP server (stdio transport) docker run -i sktime-mcp ``` Or use Docker Compose: ```…