🚀 Northwind FastAPI MCP Example

This project demonstrates how to use fastapi-mcp to create a Model Context Protocol (MCP) server that allows Large Language Models (LLMs) to connect and interact with a REST API.

📋 Overview

The Northwind API is a simple example that shows how to expose data from the classic Northwind database through both a traditional REST API and an MCP endpoint, making it accessible for LLMs to query and understand.

Related MCP server: SQL Server MCP

🏁 Getting Started

Prerequisites

• Python 3.10+ 🐍

• Virtual environment tool 🔧

Installation

1. Clone the repository and install dependencies:

   git clone https://github.com/RobertoRuben/mcp-northwind-fastapi-example.git
   cd mcp-northwind-fastapi-example
   python -m venv venv
   venv\Scripts\activate  # On Windows
   pip install -r requirements.txt

2. Run the application:

   uvicorn src.main:app --reload

3. Access the API documentation at http://localhost:8000/api/v1/docs 📝

🔌 Available Endpoints

REST API Endpoints

• GET /api/v1/products: List all products 📦

MCP Endpoint

• http://localhost:8000/mcp: Model Context Protocol endpoint for LLM connections 🤖

🔗 Connecting an LLM to the API

This example demonstrates how fastapi-mcp creates a bridge between your REST API and Large Language Models:

1. Traditional REST endpoints serve structured data at /api/v1/products* 📊

2. The MCP endpoint at /mcp allows LLMs to discover and interact with your API programmatically 🧠

3. LLMs can understand your data schema and execute appropriate API calls automatically. ✨