Microsoft Reactor Stockholm

In the intro session of our Python + MCP series, we dive into the hottest technology of 2025: MCP (Model Context Protocol). This open protocol makes it easy to extend AI agents and chatbots with custom functionality, making them more powerful and flexible.

We demonstrate how to use the Python FastMCP SDK to build an MCP server running locally and consume that server from chatbots like GitHub Copilot. Then we build our own MCP client to consume the server.
Finally, we discover how easy it is to connect AI agent frameworks like Langchain and Microsoft agent-framework to MCP servers.

📌 This session is a part of a series. Learn more here

In our second session of the Python + MCP series, we're deploying MCP servers to the cloud! We'll walk through the process of containerizing a FastMCP server with Docker and deploying to Azure Container Apps, and also demonstrate a FastMCP server running directly on Azure Functions.

Then we'll explore private networking options for MCP servers, using virtual networks that restrict external access to internal MCP tools and agents.

In our third session of the Python + MCP series, we're exploring the best ways to build authentication layers on top of your MCP servers. That could be as simple as an API key to gate access, but for the servers that provide user-specific data, we need to use an OAuth2-based authentication flow.

MCP authentication is built on top of OAuth2 but with additional requirements like PRM and DCR/CIMD, which can make it difficult to implement fully. In this session, we'll demonstrate the full MCP auth flow, and provide examples that implement MCP Auth on top of Microsoft Entra.