# MCP Data Analyst

A lightweight Model Context Protocol (MCP) server built with Python and Pandas that exposes reusable data-analysis capabilities as MCP tools.

## Overview

This project demonstrates how an MCP-compatible client can discover and invoke external data-analysis tools through a standardized MCP server.

The server analyzes a sample sales CSV dataset and exposes five tools:

- `dataset_info` - Returns dataset dimensions and column names
- `dataset_summary` - Returns descriptive statistics
- `missing_values` - Detects missing values
- `sales_by_region` - Filters sales records by region
- `column_analysis` - Calculates statistics for numeric columns

## Architecture

User / AI Host
        |
        v
MCP Client
        |
        v
MCP Server
        |
        v
MCP Tools
        |
        v
Python + Pandas
        |
        v
Sales CSV Dataset

## Project Structure

mcp-data-analyst/
├── data/
│   └── sample_sales.csv
├── tests/
│   └── test_analysis.py
├── tools/
│   ├── __init__.py
│   ├── analysis_tools.py
│   └── csv_tools.py
├── server.py
├── requirements.txt
├── pytest.ini
├── .gitignore
└── README.md

## Technologies

- Python
- Model Context Protocol (MCP)
- Pandas
- Pytest
- MCP Inspector

## Installation

Create and activate a virtual environment.

Windows PowerShell:

```powershell
python -m venv venv
.\venv\Scripts\Activate.ps1