Connects Claude to Apache Parquet files, the columnar storage format widely used in data engineering and analytics pipelines. Part of the CLIO Kit scientific computing toolkit from IoWarp, which packages 16 MCP servers for HPC and research workflows. You'd reach for this when working with large datasets stored in Parquet format and want to query, inspect, or transform them through natural language. The broader clio-kit package includes servers for HDF5, pandas DataFrames, Slurm job submission, and ArXiv paper search, all installable via uvx. Designed for researchers and data scientists who need AI assistance with scientific data formats without writing custom parsing scripts each time.
claude mcp add --transport stdio io.github.iowarp-parquet-mcp uvx parquet-mcp