How to Build an MCP Server in Python with FastMCP

Overview

Short answer: to build an MCP server in Python, install the official MCP Python SDK (uv add "mcp[cli]" or pip install "mcp[cli]"), create a FastMCP server, turn ordinary Python functions into tools with the @mcp.tool() decorator, and start it with mcp.run(). Then add the server to your MCP client's config (for example Claude Desktop's claude_desktop_config.json) so the model can call your tools.

The rest of this tutorial does exactly that, step by step. You'll build an MCP server that wraps a Weather API, learning each concept as we go. We start with the simplest possible server and incrementally add production features.

What you'll learn:

• What MCP is and how it works
• Building tools, resources, and prompts
• Proper error handling and logging
• Deploying to production

Prerequisites: Python 3.10+, async/await familiarity, REST API basics