FastMCP 101: build, test, and deploy your first MCP server in Python (FastMCP 4). Companion to the FastMCP Foundations Instruqt track.
View on GitHub ↗Build, test, and deploy your first MCP server in Python. No prior MCP experience needed.
The Model Context Protocol (MCP) is the shared standard that lets AI assistants use outside systems: your data, your APIs, your expertise. You build a server that offers capabilities; any MCP client (Claude, ChatGPT, Cursor, an agency chatbot) can then use them. Think of it as the wall outlet between assistants and the systems you own. The utility doesn't care what you plug in.
FastMCP is the Python framework that makes a server out of ordinary functions. One decorator per function. This repo pins FastMCP 4.
A weather server with three tools, one resource, and one prompt, backed by Open-Meteo (free, no API key). By the end you will have run it locally, tested it in memory, and deployed it to a public URL on Prefect Horizon.
Lesson You will Time --------- 1. Build your first MCP server Write a one-tool server and call it from the CLI 10 min 2. Turn functions into tools Decorate three weather functions and read the schema the AI sees 15 min 3. Add resources and prompts Give the assistant something to read and a saved recipe 10 min 4. Test your server with code Use the in-memory client and run the test suite 10 min 5. Deploy to Prefect Horizon Run over HTTP, push to GitHub, deploy, chat with it 20 min
The lessons live in WORKSHOP.md. Follow them in order.
Prefer a browser sandbox with nothing to install? The same course runs on Instruqt: FastMCP Foundations.
From the project README.
Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:
[](https://mcp.liqiwa.com/s/prefectlabs--fastmcp-101.html)
Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is
zhuyansen/new-term-radarDaily radar for new AI terms: names of new models, products and repos, caught on X, Hugging Face, GitHub and sitemaps before keyword tools list them.
yzg1226/mcd-party-officer🍟 麦当劳门店派对成团调度 Skill — 把派对从「策划」推进到「办得成」：成团概率雷达 / 包场vs拼团 / 择日黄历 / 儿童营养指数 / 招募卡与邀请函
fellowgeek/mcp-memoryAn OKF-backed Model Context Protocol (MCP) server delivering persistent long-term memory and SQLite FTS5 search for AI agents.
hirotomasato/yowesGenerate realistic teacher documents (ID cards, licenses, letters) for 13 countries via MCP.
hujjun/mcd-saver-strategist麦当劳省钱点餐助手（麦门精算师）｜麦当劳优惠券组合优化 Skill：拉取麦当劳菜单与全部可用优惠券，算出最省的点餐组合，巨无霸套餐 ¥47 → ¥21.9（省 53%）。McDonalds MCP（麦当劳 MCP）coupon optimizer · McDonalds China MCP Server · Agent Skill for WorkBuddy · 麦当劳程序员创意开发大赛参赛作品
The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.