MCP Developer Quick Start

Introduction

MCP is an open protocol that standardizes how applications provide context to LLMs. Think of MCP like a USB-C port for AI applications. Just as USB-C provides a standardized way to connect your devices to various peripherals and accessories, MCP provides a standardized way to connect AI models to different data sources and tools.

Prerequisites

• A Linux or macOS system
• Python 3.8 or later installed
• pip package manager installed

Installation

Build Virtual Env

For Python developers, it is always good to use virtual environment to isolate your different test environments.

gyliu513@Guangyas-MacBook-Pro ~ % python3.10 -m venv mcp
gyliu513@Guangyas-MacBook-Pro ~ % source mcp/bin/activate
(mcp) gyliu513@Guangyas-MacBook-Pro ~ %

Install MCP

(mcp) gyliu513@Guangyas-MacBook-Pro ~ % pip install "mcp[cli]"

Create a sample server

Let’s create a simple MCP server that exposes a calculator tool and some data:

# demo.py
from mcp.server.fastmcp import FastMCP
# Create an MCP server
mcp = FastMCP("Demo")

# Add an addition tool
@mcp.tool()
def add(a: int, b: int) -> int:
    """Add two numbers"""
    return a + b

# Add a dynamic greeting resource
@mcp.resource("greeting://{name}")
def…