Local MCP server for GPU-backed TimesFM 2.5 forecasting, enabling zero-shot time-series forecasting, covariate forecasting, anomaly detection, and CSV forecasting via MCP tools.
MCP server for predictalot, providing streamable HTTP tools for zero-shot time-series forecasting with multiple foundation models and per-type ensembles. Tabular ML endpoints are currently HTTP-only.
Enables training and using machine learning models on local CSV datasets or data from other MCP servers, supporting tasks like forecasting, regression, classification, and anomaly detection.
An MCP server powered by Meta's Prophet that enables LLMs to perform time-series forecasting, trend analysis, and predictive modeling on historical data. It provides LLM-friendly statistical summaries, automated business-rule validation, and ready-to-render Chart.js visualizations.