Skip to content
Agentmart
Submit a tool

Auto TS

Automated time series forecasting with model search, anomaly detection, and event risk analysis

Connector by winedarksea · GitHub account verified by the MCP Registry

IndexedMITLocal (stdio)★ 1,434
Write a review

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/winedarksea-autots

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Automated time series forecasting with model search, anomaly detection, and event risk analysis

Use cases: data-analysis, data-visualization

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools
12 read · 10 write · 6 delete
Secrets
None asked for
Install scripts
Not scanned yet
Runs as
Python package

Tools by what they do 28

Read from the source code; the running server may list different tools.

Read 12 · Look things up without changing anything.

  • get_data
  • get_detected_features
  • get_event_risk_results
  • get_forecast
  • get_forecast_components
  • get_model_params
  • get_validation_results
  • list_cache
  • plot_event_risk
  • plot_features
  • plot_forecast
  • plot_validation

Write 10 · Create, change, send or run things.

  • apply_adjustments
  • apply_constraints
  • convert_long_to_wide
  • detect_features
  • forecast_custom
  • forecast_event_risk
  • forecast_explainable
  • forecast_fast
  • forecast_from_features
  • load_sample_data

Delete 6 · Delete, drop, revoke or wipe things.

  • clean_data
  • clear_cache
  • generate_synthetic_data
  • load_data_from_file
  • load_live_data
  • smart_load

Files it touches

  • Any path the agent passes to its tools

Tools (28)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

  • apply_adjustmentsApply Forecast Adjustments

    Apply post-hoc adjustments to a forecast. Requires prediction_id from a forecast tool. Three types: 1) 'basic'/'linear'/'ramp' — linear ramp between start/end dates with start/end values (additive or multiplicative); 2) 'align_last_value'/'alignlastvalue' — align forecast to recent history (also requires data_id); 3) 'smoothing'/'ewma' — exponential smoothing with span parameter. Optionally restrict to specific series_ids. Returns new prediction_id.

  • apply_constraintsApply Forecast Constraints

    Apply constraints to a forecast (dampen growth, enforce upper/lower bounds, or quantile clipping). Requires prediction_id from a forecast tool. Returns a new prediction_id with constrained values.

  • clean_dataClean Time Series Data

    Clean time series data: fill missing values and handle outliers. Provide either data (inline dict) or data_id. Returns new data_id with cleaned data.

  • clear_cacheClear Cachecan change or delete data

    Clear cache: specific object by ID+type, an entire cache type, or all caches. Destructive — freed objects cannot be recovered.

  • convert_long_to_wideConvert Long Format to Wide

    Convert long-format data (datetime, series_id, value columns) to wide format. Provide either data (inline dict) or data_id. Returns new data_id.

  • detect_featuresDetect Time Series Features

    Detect anomalies, changepoints, level shifts, holidays, and seasonality patterns across all series. Provide data or data_id. Returns detector_id for use in get_detected_features, plot_features, and forecast_from_features.

  • forecast_customCustom AutoTS Forecast

    CUSTOM: AutoTS with user-specified parameters or template. Use when forecast_fast results are insufficient. Read the autots://docs/forecast_custom_params resource for available parameters. Defaults to 'scalable' model_list. Provide data or data_id. Returns prediction_id and autots_id.

  • forecast_event_riskForecast Event Risk Probabilities

    Forecast the probability of crossing a threshold over future periods (e.g., stockout risk, capacity breach). Threshold in [0,1] is treated as a historical quantile; values outside [0,1] are absolute. Provide data or data_id. Returns event_risk_id for use in get_event_risk_results and plot_event_risk.

  • forecast_explainableExplainable Model Forecast

    MODERATE: AutoTS model search restricted to EXPLAINABLE models (Cassandra, TVVAR, BasicLinearModel). Use when interpretability matters. Provide data or data_id. Returns prediction_id and autots_id. Use get_forecast_components on prediction_id for component decomposition.

  • forecast_fastFast Mosaic Ensemble Forecast

    FAST: Pre-configured mosaic ensemble forecast using fit_data (no model search). Use for quick results. Provide data or data_id. Returns prediction_id for use in get_forecast, plot_forecast, apply_constraints, apply_adjustments, get_model_params.

  • forecast_from_featuresForecast from Detected Features (Experimental)

    EXPERIMENTAL: Create a forecast using the decomposed components from a feature detector. Only use after detect_features, not as a standalone forecasting method. Requires detector_id from detect_features. Returns prediction_id for use in get_forecast, plot_forecast.

  • generate_synthetic_dataGenerate Synthetic Time Series

    Generate synthetic time series data with labeled components for testing. Returns data_id.

  • get_dataGet Cached Dataread-only

    Retrieve cached data as JSON (wide or long) or save as CSV. Requires data_id from load_sample_data, load_live_data, load_data_from_file, generate_synthetic_data, convert_long_to_wide, or clean_data.

  • get_detected_featuresGet Detected Featuresread-only

    Query detected features (anomalies, changepoints, level shifts, holidays, seasonality) from a cached detector. Requires detector_id from detect_features. Supports filtering by date range, specific date, or series name. Use include_components=true for time-series component values. Examples: 'was there an anomaly on 2024-12-25?', 'when was the first level shift?'

  • get_event_risk_resultsGet Event Risk Probabilitiesread-only

    Get event risk probability values from a cached EventRiskForecast. Requires event_risk_id from forecast_event_risk. Returns probabilities per period per series.

Show 13 more tools
  • get_forecastGet Forecast Dataread-only

    Retrieve forecast values from a cached prediction as JSON or CSV. Requires prediction_id from forecast_fast, forecast_explainable, forecast_custom, or forecast_from_features. Use output='all' to get point, upper, and lower forecasts combined with a forecast_type column.

  • get_forecast_componentsGet Forecast Component Decompositionread-only

    Get decomposed forecast components (trend, seasonality, etc.) if available. Only works for Cassandra and TVVAR models — use forecast_explainable to guarantee these model types. Requires prediction_id.

  • get_model_paramsGet Model Parametersread-only

    Get model name, parameters, and transformation parameters from a cached prediction. Requires prediction_id from any forecast tool.

  • get_validation_resultsGet Validation Resultsread-only

    Get cross-validation results and top model rankings from an AutoTS model search. Requires autots_id from forecast_explainable or forecast_custom.

  • list_cacheList Cached Objectsread-only

    List all cached objects across all cache types (predictions, autots_models, event_risk, feature_detectors, data). Call this to discover existing IDs before calling any get_*, plot_*, or apply_* tools.

  • load_data_from_fileLoad Data from File or URL

    Load a CSV from a local file path or URL. Returns data_id. CSV must have a datetime column as the first column (index).

  • load_live_dataLoad Live Data (FRED / Stocks)

    Load live data from external sources (FRED economic data, stock tickers). Returns data_id. Requires network access.

  • load_sample_dataLoad Sample Dataset

    Load a built-in sample time series dataset. Returns data_id for use as the data_id parameter in forecast_*, detect_features, forecast_event_risk, clean_data, and get_data.

  • plot_event_riskPlot Event Risk Probabilitiesread-only

    Plot event risk probabilities over the forecast horizon. Requires event_risk_id from forecast_event_risk. Returns base64-encoded PNG.

  • plot_featuresPlot Detected Featuresread-only

    Plot detected features overlaid on the time series. Requires detector_id from detect_features. Returns base64-encoded PNG.

  • plot_forecastPlot Forecastread-only

    Plot forecast with optional history and prediction intervals. Requires prediction_id from forecast_fast, forecast_explainable, forecast_custom, or forecast_from_features. Returns base64-encoded PNG image. Defaults to first series only.

  • plot_validationPlot Validation Forecastsread-only

    Plot cross-validation forecasts from an AutoTS model search. Requires autots_id from forecast_explainable or forecast_custom. Returns base64-encoded PNG.

  • smart_loadSmart Load (paste / upload / URL)

    Beginner-friendly data loader. Accepts pasted CSV/TSV text, a CSV URL (e.g. a published Google Sheet), or base64-encoded file bytes (CSV or XLSX). Automatically removes empty/padding rows and columns, detects wide vs long orientation, and returns a data_id plus a report describing what was cleaned and detected. Prefer this over load_data_from_file for raw human spreadsheets.

Signals

Stars
1,434
Forks
127
Open issues
25
Contributors
1
Weekly downloads
84
Last commit
Aug 20, 2026 (2 months ago)
Last release
Aug 20, 2026 (2 months ago)
Last package publish
Jan 30, 2026 (9 months ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Registry name
io.github.winedarksea/AutoTS
Version
1.0.1
Auth
No auth
Packages
pypi autots-mcp
License
MIT
Repository
github.com/winedarksea/AutoTS
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
Official MCP Registrygithub-graphql
Cite this page

Auto TS MCP server. Agent Mart. https://agentmart.dev/connectors/winedarksea-autots (last updated 2026-10-24)