Advanced MCP Features 🐡

Intro

👨‍💼 Hello, my name is Peter the Product Manager. I'm here to help you get oriented and to give you your assignments for the workshop!
Welcome to Advanced MCP Features! In this workshop, you'll dive into the world of the Model Context Protocol (MCP)—an open protocol designed to seamlessly connect AI models with external data sources and tools. We'll be going deeper on the MCP spec and how to use it to build more advanced AI connected apps.
We'll focus on advanced features of the spec, however we'll not be covering authentication or authorization (that's an entire workshop in itself).
We'll be using the MCP TypeScript SDK to build our MCP server and the MCP Inspector to test it.
If you're curious about the details, I highly recommend checking out the official MCP specification and the introduction. These resources provide a deep dive into the protocol, its design principles, and practical implementation tips.
NOTE: At the time of this writing, some clients don't support the features that we're going to be learning about in this workshop. Notably, the best clients which support most of these features are VSCode and nanobot.ai. If you're using another client, you may not be able to test all the features in this workshop.
Ready to build even better AI connected apps? Then let's get going!