haiiibin/data-profiler-mcp

What it does

haiiibin/data-profiler-mcp is an MCP (Model Context Protocol) server that profiles and analyzes tabular data files for large language model agents. It processes multiple file formats including CSV, TSV, Parquet, Excel, and JSON files, delivering comprehensive data insights in a single call.

Key features

• Dataset overview and summary statistics
• Per-column statistical analysis
• Data quality audit including missing values, duplicates, mixed types, and outlier detection
• Memory-saving dtype optimization suggestions
• Support for multiple file formats (CSV, TSV, Parquet, Excel, JSON)
• Pure Python implementation for easy deployment
• Cross-platform compatibility (Windows, macOS, Linux)

How to set up

Install the MCP server following the standard MCP protocol setup. Configure it with your Claude or compatible AI client to enable data profiling capabilities. The tool requires Python and standard data analysis libraries for operation.