sktime-mcp

Read the Official Documentation | PyPI Package

The Semantic Engine for Time-Series

Enables Large Language Models to discover, reason about, and execute sktime's advanced forecasting algorithms on real-world data.

Why sktime-mcp? Combines LLM reasoning with time-series precision. Instead of hallucinating Python code, your agent interacts with a strictly typed, safe, and stateful API to perform complex forecasting tasks.

👋 Who is this for?

sktime‑mcp is designed for:

  • Developers building LLM agents that need reliable, production‑grade time‑series forecasting.

  • Data scientists who want to expose sktime workflows to language models without unsafe code generation.

  • Platform teams integrating forecasting capabilities into tools like Claude Desktop, Cursor, or custom MCP clients.

If you are new to MCP‑based workflows, start with the Quick Start below, then explore the Use Cases and User Guide for deeper examples.

🔥 Key Features

  • Registry-Driven Discovery: Find estimators by capability tag and name search against the live sktime registry (e.g., “probabilistic forecaster that handles missing data”) — reading installed metadata, never recalling it from memory.

  • Composition via craft(): Build pipelines (Transformer → Forecaster) from a single spec string, validated by sktime itself, so incompatible components fail before execution.

  • Universal Data Loading: Ingest data from Pandas, SQL, URLs, and files — CSV, Excel, and Parquet.

  • Execution Runtime: Stateful engine that manages object lifecycles, fitting, predicting, and background jobs, all via MCP tool calls.

⚡ Quick Start

Get up and running in seconds. Use with Claude Desktop, Cursor, or any MCP-compatible client.

1. Install

Zero-install via uvx (recommended): if you have uv installed, skip this step — uvx fetches and runs the package automatically when your MCP client starts.

# Or install explicitly with pip
pip install sktime-mcp

When contributing, install from source:

git clone https://github.com/sktime/sktime-mcp.git
cd sktime-mcp
python3 -m venv .venv
source .venv/bin/activate
pip install -e ".[dev]"

2. Connect (Claude Desktop / Claude Code Config)

Add this to your claude_desktop_config.json:

With uvx (no prior install needed):

{
  "mcpServers": {
    "sktime": {
      "command": "uvx",
      "args": ["sktime-mcp"]
    }
  }
}

With pip-installed package:

{
  "mcpServers": {
    "sktime": {
      "command": "sktime-mcp"
    }
  }
}

📚 Documentation Map

Section

Description

Installation

Install methods, optional extras, and verification.

Quickstart

Fastest route to running the sktime-mcp server and connecting it to a client.

Concepts

Core concepts, handles, and asynchronous operations.

User Guide

Hands-on walkthrough with four worked end-to-end workflows.

Tool Reference

Every MCP tool, its arguments, and what it returns.

Architecture

High-level system design, data flow, and the trust boundary.

Contributing

Contributing guidelines, testing, and extending the server.

🚀 Get Started