Data Profiler Mcp

Overview

Data Profiler Mcp is a Model Context Protocol server that analyzes CSV, Parquet, Excel, and JSON files to extract schema information, statistical summaries, data quality flags, and data type recommendations. It enables LLM agents to profile and understand data files directly without manual inspection or context switching.

The server runs locally via the uvx command: uvx data-profiler-mcp. It requires no authentication and operates over stdio on your machine using the data-profiler-mcp Python package. Version v0.3.0 is published under the MIT license with source code available at haiiibin/data-profiler-mcp on GitHub.

Data Profiler Mcp belongs in the AI & Agents category on mcp.site and works with any MCP-compatible client including Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, and Zed. If you maintain this project, claim the listing to verify ownership and keep information current.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "data_profiler_mcp": {
      "command": "uvx",
      "args": [
        "data-profiler-mcp"
      ]
    }
  }
}