sktime-mcp¶
The Semantic Engine for Time-Series
Empower Large Language Models to discover, reason about, and execute sktime's advanced forecasting algorithms on real-world data.
Why sktime-mcp? Bridging the gap between LLM reasoning and time-series precision. Instead of hallucinating Python code, your agent interacts with a strictly typed, safe, and stateful API to perform complex forecasting tasks.
🔥 Key Features¶
- Semantic Discovery: Find the perfect estimator using semantic similarity and capability tags (e.g., "probabilistic forecaster that handles missing data").
- Safe Composition: Build complex pipelines (Transformer → Forecaster) with built-in validation to ensure components are compatible before execution.
- Universal Data Loading: Seamlessly ingest data from SQL, Pandas, Parquet, Excel, and CSV files.
- Execution Runtime: Stateful engine that manages object lifecycles, fitting, and predicting, all via simple JSON-RPC tools.
âš¡ Quick Start¶
Get up and running in seconds. Use with Claude Desktop, Cursor, or any MCP-compatible client.
1. Install¶
git clone https://github.com/Shashankss1205/sktime-mcp.git
cd sktime-mcp
python3 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt
pip install -e .
2. Run¶
3. Connect (Claude Desktop Config)¶
Add this to your claude_desktop_config.json:
📚 Documentation Map¶
| Section | Description |
|---|---|
| Use Cases | Step-by-step workflows for coders and business users. |
| User Guide | Comprehensive manual on using tools, workflows, and best practices. |
| Usage Examples | Example scripts and advanced usage patterns. |
| Data Sources | Deep dive into loading data from SQL, Files, and Pandas. |
| Architecture | High-level system design, data flow, and limitations. |
| Implementation | Detailed code walkthrough and file breakdown. |
| Developer Guide | Contributing guidelines, testing, and extending the server. |
🚀 Get Started¶
- See Use Cases for step-by-step workflows.
- See User Guide for detailed instructions and advanced features.