Product MCP Server

This project implements a simple Model Context Protocol (MCP) server using FastMCP, Pydantic, and Uvicorn.
It exposes three tools:

• Add Product

• Search Product

• Get Product by ID

Products are stored in an in-memory database, making this ideal for demos, prototyping, or integrating with an MCP-compatible AI agent.

Features

• FastMCP-based MCP server

• Tool functions to:

• Add a new product

• Search products by name or category

• Retrieve product details by ID

• Simple in-memory storage

• Runs over HTTP using Uvicorn

Installation

1. Create a virtual environment

2. Install dependencies

Running the Server

Start the MCP server:

The server will start on:

Available Tools

1. add_product

Adds a new product to the in-memory catalog.

Input Model (AddProductInput)

2. search_product

Searches for products by name or category.

Input Model (SearchInput)

3. get_product

Gets a product by its unique ID.

Input Model (GetProductInput)

MCP Client Example

Run the client