// MCP TOOL REFERENCE

SKTIME TOOLS

24 tools from the Sktime MCP Server, categorised by risk level.

// ALL 24 SKTIME TOOLS

READ 12 tools

Read check_job_status Check the status and progress of a background job Read describe_estimator Get detailed information about a specific sktime estimator Read get_available_tags List all queryable capability tags with rich metadata. Read list_available_data List all data available for use — system demo datasets and active Read list_estimators Discover sktime estimators by task, capability tags, or name search. Read list_handles List all active estimator handles in memory Read list_jobs List all background jobs with optional status filter Read load_data_source Load data from various sources into a data handle for forecasting. Read load_data_source_async Load data from any source in the background Read load_model Load a saved sktime model from a local path and register it for use Read validate_pipeline Check if a pipeline composition is valid Read export_code Export an estimator or pipeline as executable Python code

WRITE 4 tools

Write format_time_series Automatically format time series data (frequency, duplicates, missing values) Write instantiate_pipeline Create a pipeline instance from a list of components Write release_handle Release an estimator handle and free it from memory Write save_model Save an estimator/pipeline handle using sktime MLflow integration

DESTRUCTIVE 2 tools

Destructive cancel_job Cancel a running or pending background job. Destructive release_data_handle Release a data handle and free memory

EXECUTE 6 tools

Execute evaluate_estimator Evaluate an estimator using cross-validation on a dataset Execute fit_predict Fit an estimator and generate predictions. Execute fit_predict_async Fit an estimator and generate predictions in the background. Execute fit_predict_classification Fit a time series classifier on training data and predict class labels on test data. Use with classificatio... Execute fit_predict_regression Fit a time series regressor on training data and predict continuous target values on test data. Use with re... Execute instantiate_estimator Create an estimator instance with given parameters

// FAQ

How many tools does the Sktime MCP server have? +

The Sktime MCP server exposes 24 tools across 4 categories: Read, Write, Destructive, Execute.

How do I enforce policies on Sktime tools? +

Route the Sktime server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard; they are enforced on every call before it reaches the server.

What risk categories do Sktime tools fall into? +

Sktime tools are categorised as Read (12), Write (4), Destructive (2), Execute (6). Each category has a recommended default policy.

Enforce policy on every Sktime tool call.

Start from Sktime, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →

Free to start. No card required.

43,000+ MCP servers and 220,000+ tools scanned and risk-classified.