MCP on Azure at real scale: Container Apps, KEDA autoscaling, a gateway in front, and the SSE-behind-a-load-balancer gotcha that quietly breaks streaming.
An agent that 'feels off' tells you nothing. Here's how to make MCP observable — one trace per agent run, structured logs, and the metrics that matter.
A tool result can carry the attack. Here's how to secure MCP against prompt injection, poisoned servers, and tool abuse — and break the lethal trifecta.