mcp-data-metadata

alcides-nolasco/mcp-data-metadata

3.1

If you are the rightful owner of mcp-data-metadata and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to dayong@mcphub.com.

The Model Context Protocol (MCP) server is a Python-based tool designed to extract metadata, statistics, and data samples from various file formats, enhancing the context for language models or AI agents.

📊 Data Metadata MCP

Model Context Protocol (MCP) server written in Python to extract metadata, statistics, and data samples from files in CSV, Excel, JSON, and Parquet formats.

This MCP is ideal for enriching the context of language models or AI agents that need to analyze the structure and content of data before generating code or performing analysis.

✨ Features

  • 📂 Supports formats: CSV, Excel (.xls / .xlsx), JSON, and Parquet.
  • 📏 Returns metadata: number of rows, columns, data types, file size.
  • 📊 Computes basic statistics: means, counts, and null values.
  • 🗂 Extracts schema and internal metadata from Parquet files.
  • 👀 Shows real data samples (first rows).
  • ⚡ Compatible with any MCP client (Claude Desktop, VSCode MCP extension, etc.).

📦 Installation

  1. Clone the repository

    git clone https://github.com/alcides-nolasco/mcp-data-metadata.git
cd mcp-data-metadata

  2. create a virtual environment (optional but recommended) python3 -m venv venv source venv/bin/activate # On Windows use venv\Scripts\activate

  3. Install dependencies

pip install -r requirements.txt 4. Run the server

python mcp_server.py