$ loading_
Enable LLMs to discover, compose, and run sktime forecasting workflows.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "sktime-mcp" yet — see the docs or source repo.
Using sktime-mcp, recommend a suitable time-series forecasting workflow for monthly sales data, explain the model choice, then train it and forecast the next 6 months.
A runnable sktime workflow, rationale for model selection, and 6-month forecast results.
Use sktime-mcp to find models suitable for seasonal time series, compare at least three estimators with pros, cons, and evaluation results, and recommend the best option.
A list of candidate models, performance comparison, scenario analysis, and a final recommendation.
Through sktime-mcp, discover available preprocessing, feature transformation, and forecasting components, automatically compose them into an end-to-end workflow, and execute it.
A complete time-series modeling pipeline that is generated and executed, with step descriptions and results.
Train, compare, and forecast time series with deep learning models.
Call tools like weather lookup via MCP with reusable resources and prompts.
Use MCP tools to analyze GitHub repos, calculate, check weather/time, and run commands.
Connect to Jupyter via MCP to run code and explore data interactively.
Manage projects and run evaluation, comparison, splitting, and analysis via MCP.
Demo MCP server for calculations, time checks, notes, and code review prompts.