"NumPy" matching MCP servers:

A Model Context Protocol (MCP) server that provides mathematical calculations and operations using NumPy, enabling users to perform numerical computations like matrix operations, statistical analysis, and polynomial fitting directly through Claude.

Enables MCP clients to upload tabular datasets and run deterministic Pandas, NumPy, Excel/openpyxl, and automated EDA operations through registered tools.

Memory for facts that change. A retrieved record is marked SUPERSEDED, with when a later record replaced it, so an assistant does not answer with a value that is no longer true. Single file, numpy the only dependency, runs with a local embedding model or none at all.

Enables LLM clients to analyze numerical data series (NumPy, Pandas, Polars, lists) and receive token-efficient natural-language summaries of trend, volatility, anomalies, seasonality, and data quality instead of raw values. Supports single-series analysis, batch processing of multiple series, and structured JSON output.