MCP is one of the fastest growing technologies in the Generative AI space this year, and the first AI related standard that the industry has really embraced wholeheartedly. I just gave a three-part live stream series all about Python + MCP. I showed how to:
- Build MCP servers in Python using FastMCP
- Deploy them into production on Azure (Container Apps and Functions)
- Add authentication, using either Keycloak and Microsoft Entra as the OAuth provider
All of the materials from our series are available and linked below:
- Video recordings of each stream
- Powerpoint slides
- Open-source code samples complete with Azure infrastructure and 1-command deployment
If you're an instructor, feel free to use the slides and code examples in your own classes.
Spanish speaker? My colleague delivered a fantastic Spanish version of the series.
Building MCP servers with FastMCP
In the intro session of our Python + MCP series, we dive into 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. Then we consume that server from chatbots like GitHub Copilot in VS Code, using it's tools, resources, and prompts. Finally, we discover how easy it is to connect AI agent frameworks like Langchain and Microsoft agent-framework to the MCP server.
Deploying MCP servers to the cloud
In our second session of the Python + MCP series, we deploy MCP servers to the cloud! We walk through the process of containerizing a FastMCP server with Docker and deploying to Azure Container Apps. Then we instrument the MCP server with OpenTelemetry and observe the tool calls using Azure Application Insights and Logfire. Finally, we explore private networking options for MCP servers, using virtual networks that restrict external access to internal MCP tools and agents.
Authentication for MCP servers
In our third session of the Python + MCP series, we explore the best ways to build authentication layers on top of your MCP servers. We start off simple, with an API key to gate access, and demonstrate a key-restricted FastMCP server deployed to Azure Functions. Then we move on to OAuth-based authentication for MCP servers that provide user-specific data. We dive deep into MCP authentication, which is built on top of OAuth2 but with additional requirements like PRM and DCR/CIMD, which can make it difficult to implement fully. We demonstrate the full MCP auth flow in the open-souce identity provider KeyCloak, and show how to use an OAuth proxy pattern to implement MCP auth on top of Microsoft Entra.