sktime-mcp

The Semantic Engine for Time-Series with Large Language Models.

sktime-mcp is a Model Context Protocol (MCP) server that exposes the full power of the sktime ecosystem to AI assistants. It provides a stateful runtime for discovering, instantiating, and executing time-series workflows — forecasting, classification, regression, transformation, detection, and splitting.

Forecasting is the most polished path today; the other scitypes are reachable through generic instantiation and call_method. See MCP Tool Reference for what is available.

Getting Started

• sktime-mcp
  • 👋 Who is this for?
  • 🔥 Key Features
  • ⚡ Quick Start
  • 📚 Documentation Map
  • 🚀 Get Started
• Installation
  • Prerequisites
  • Standard Installation
  • Developer Installation
  • Verification
• Quickstart
  • 1. Start the Server
  • 2. Connect to a Client
  • 3. Verify Functionality
  • 4. Run Your First Forecast
  • Next Steps
• Core Concepts
  • Collaborative Model Discovery
  • Stateful Interaction (Handles)
  • Asynchronous Background Jobs
  • Safety and Reproducibility

User Guide

• User Guide: Conversational Time-Series Workflows
  • What This Guide Covers
  • 1. MCP + sktime-mcp
  • 2. Install and Connect
  • 3. Tool Options
  • 4. Worked Examples
  • 5. Current Limitations
  • 6. Wrap-Up
• MCP Tool Reference
  • Conventions
  • Discovery
  • Instantiation and handles
  • Execution
  • Data
  • Persistence and code generation
  • Background jobs
  • System

Developer Guide

• Architecture
  • High-Level Overview
  • Core Components
  • Data Flow: The “Handle” Pattern
  • Concurrency Model
  • Security Considerations
• Contributing Guide
  • Development Setup
  • Code Quality Standards
  • Testing
  • Project Structure
  • Documentation
  • Pull Request Process
• API Reference
  • Server
  • Tools
  • Registry
  • Runtime
  • Data
  • Configuration

Indices and tables

• Index

• Module Index

• Search Page