autots.mcp package

Submodules

autots.mcp.server module

MCP Server for AutoTS Time Series Forecasting

This server exposes AutoTS forecasting and analysis functions as MCP tools for integration with LLM environments like VS Code.

autots.mcp.server.build_csv_metadata(filepath: str, df: DataFrame, is_long: bool = False) → dict

Build metadata for CSV export with loading instructions.

Parameters:

• filepath – Path to CSV file

• df – DataFrame that was saved

• is_long – Whether CSV is in long format

Returns:

Metadata dictionary with loading instructions

autots.mcp.server.cache_object(obj: Any, cache_type: str, metadata: dict | None = None) → str

Cache an object and return a unique ID.

Parameters:

• obj – Object to cache

• cache_type – Type of cache (‘prediction’, ‘autots’, ‘event_risk’, ‘feature_detector’, ‘data’)

• metadata – Optional metadata

Returns:

Unique object ID

autots.mcp.server.clear_cache(obj_id: str | None = None, cache_type: str | None = None)

Clear cache - specific ID, specific type, or all if both None.

autots.mcp.server.dataframe_to_output(df: DataFrame, output_format: str = 'json_wide', save_path: str | None = None) → dict | str

Convert DataFrame to requested output format (token-efficient).

Parameters:

• df – DataFrame with DatetimeIndex

• output_format – “json_wide”, “json_long”, “csv_wide”, “csv_long”

• save_path – Optional path to save CSV (returns path)

Returns:

Dictionary (JSON) or string (CSV path)

autots.mcp.server.get_cached_object(obj_id: str, cache_type: str) → Dict[str, Any]

Retrieve a cached object by ID and type.

autots.mcp.server.list_all_cached_objects() → dict

List all cached objects across all cache types.

autots.mcp.server.load_to_dataframe(data: dict | str | None = None, data_format: str = 'wide', data_id: str | None = None) → DataFrame

Load data to pandas DataFrame from multiple sources.

Parameters:

• data – JSON dict, CSV file path, or URL. If None, must provide data_id

• data_format – “wide” or “long” (for JSON input)

• data_id – Optional cached data ID to load from cache

Returns:

DataFrame with DatetimeIndex

autots.mcp.server.save_temp_csv(df: DataFrame, is_long: bool = False) → str

Save DataFrame to temporary CSV file.

Parameters:

• df – DataFrame to save

• is_long – Convert to long format before saving

Returns:

Full path to saved CSV

autots.mcp.server.serialize_timestamps(obj)

Recursively convert pandas Timestamp objects to strings for JSON serialization.

Parameters:

obj – Object that may contain Timestamp objects

Returns:

Object with Timestamps converted to strings

autots.mcp.server.serve()

Start the MCP server.

Module contents

Model Context Protocol (MCP) Server for AutoTS

This package provides an MCP server interface for AutoTS forecasting capabilities, enabling LLM integration for time series forecasting tasks.

autots.mcp.serve()

Start the MCP server.