Offline MCP server that queries CSV, Parquet, Excel, and JSON files and generates self-contained interactive HTML reports with reproducible provenance. Built and maintained by an AI agent.
A research-informed MCP server that enables natural language question answering over local dataframes (CSV, Parquet, or Pandas) with safe, read-only execution and typed analysis plans.
MCP server that turns coding agents into data analysts: attach CSV/Parquet/JSON/XLSX or databases, profile data, run read-only SQL, and render Vega-Lite charts as SVG files.
Read-only MCP server for SQL databases (SQL Server, Postgres, SQLite) with multi-server support and three-layer safety using AST validation and linting.
An MCP server that answers natural-language questions over CSV, Excel, and SQL data by providing deterministic tools for loading, profiling, querying, cleaning, statistical analysis, visualization, and reporting. It enables LLMs to plan and interpret while all computation is done exactly through MCP tools.