mcp-server-data-exploration
Author: reading-plus-ai
Description: MCP Server that equips Claude Desktop with an “explore-data” prompt template plus two tools (load-csv and run-script) for fully-automated, conversational data exploration.
Stars: 448
Forks: 47
License: MIT License
Category: Open Source
Overview
Installation
1. Clone the repository
git clone https://github.com/reading-plus-ai/mcp-server-data-exploration.git
cd mcp-server-data-exploration2. Create and activate a Python virtual environment (recommended)
python -m venv .venv
source .venv/bin/activate # On Windows: .venv\Scripts\activate3. Install Python dependencies
pip install -r requirements.txt4. Copy the example env file (if provided) and adjust credentials / ports
cp .env.example .env
# edit .env as needed5. Run database migrations or seed scripts if the project supplies them
python manage.py migrate # or a project-specific command6. Start the MCP data-exploration server
python main.py # or uvicorn/falcon/flask entry point noted in README7. Access the server (default: http://localhost:8000) or the documented API endpoints.
01
load-csv
Load a CSV file into a DataFrame
02
run-script
Execute a Python script
License: MIT License
Updated 7/30/2025