After doing these courses, I feel confident creating professional visualizations and dashboards
Shoebur RahmanProcurement Specialist, Giz Bangladesh
Course Description
Why Learn the Model Context Protocol?
Large language models can't access real-time data or take actions on their own, and wiring each tool or API with custom code doesn't scale. The Model Context Protocol (MCP) solves this with a single, standardized way for AI applications to connect to external tools, data, and services—often called "the USB-C port for AI." In this course, you'll build MCP servers and clients from scratch in Python and wire them to an LLM.How Do I Build and Connect My First MCP Server?
You'll start by learning the MCP architecture—host, client, and server—and the three primitives every server exposes: tools, resources, and prompts. Then you'll build a currency converter server using FastMCP, add docstrings and type hints so an LLM can discover your tools, and write an async Python client that lists and calls those tools over stdio transport.How Do I Give an LLM Real-Time Tools and Context?
Tools alone aren't enough—models also need data and behavioral instructions. You'll add resources for read-only context and prompts to guide the model when inputs are vague, then wire all three primitives into an OpenAI LLM using the five-step tool-calling workflow so it can answer confidently or ask for clarification when it should.How Do I Take MCP Servers to Production?
Real-world servers need more than happy-path code. You'll swap file-based resources for database-backed queries, add request timeouts, structured error handling, and secure API authentication that keeps keys server-side. Finally, you'll connect to a third-party MCP server and see that the same client code works with any server that speaks the protocol.Feels like what you want to learn?
Start Course for FreeWhat you'll learn
- Build MCP servers in Python using the MCP Python SDK, defining tools with type hints and docstrings so LLMs can discover and call them reliably.
- Connect async Python clients to MCP servers over stdio transport to list, call, and retrieve results from server-side tools, resources, and prompts.
- Integrate MCP primitives with an OpenAI LLM using the tool-calling workflow so the model can take real-world actions and respond with live data.
- Secure production MCP servers with parameterized database queries, request timeouts, structured error handling, and server-side API authentication.
- Use third-party MCP servers to add capabilities like book search without writing server code, and know how to evaluate them for trust, security, and surface area.
Prerequisites
Curriculum
Course outline
1
The Building Blocks of MCP
Discover how MCP can make integrating AI applications with surrounding systems easier than ever before! Learn about how MCP works, how to define your own MCP tools, and build the bridge between client and server.
- MCP: AI Apps as Easy as 1, 2, 350 XP
- Getting to Know MCP100 XP
- Your First MCP Server100 XP
- Building Your First MCP Server50 XP
- Building a Currency Converter MCP Server100 XP
- Adding Docstrings and Type Hints100 XP
- MCP Client-Server Communications50 XP
- Building Bridges (Between the Client and Server)100 XP
- Dynamic Tool Discoverability100 XP
- Calling Server Tools100 XP
2
MCP-Enabled LLM Applications
Add resources and prompts to MCP servers to expose LLMs to read-only context and key instructions to alter its behavior. Get hands-on with LLMs and connect them to your MCP server so it can call tools and retrieve context.
3
Preparing MCP Servers for Production
Find out what it takes to get MCP servers into production by taking a deep-dive into databases and APIs in MCP servers, and the additional considerations that they bring. Finally, integrate third-party MCPs securely and reliably, so you don't have to recreate the wheel for your favorite integrations.
Introduction to Model Context Protocol (MCP)
Course
Complete
