AI Gateway Labs
A set of over 30 hands-on Jupyter notebook labs that show how to secure, meter and observe large language models, MCP servers and AI agents behind Azure API Management's AI Gateway.
AI Gateway Labs is a collection of runnable Jupyter notebook labs built around Azure API Management's AI Gateway. Each lab deploys Bicep infrastructure templates and APIM policies into a subscriber's own Azure subscription, then walks through a specific gateway capability with step-by-step instructions.
Labs are grouped by what they secure or control: models (backend pool load balancing, token rate limiting, semantic caching, model routing, and FinOps budget quotas), tools (Model Context Protocol access with OAuth credential management, client authorization, function calling, and realtime audio combined with MCP), and agents (orchestration frameworks such as AutoGen and Foundry).
The repository also includes a developer portal starting point that can be forked and adapted with a coding agent such as GitHub Copilot.