Saul Caganoff

MCP Isn't Enough: Why Agents Needed an Event Loop, Not Just an API

Many apps are adding MCP interfaces so agents can query their systems of record. It works, until the workflows we actually care about turn out to be "something happened, now respond", and polling wastes network, context and tokens. We bolted MCP onto our product, then added events. The industry is lagging: event publication is uneven, MCP's own event support is still a draft, and agent identity and entitlements are at an early stage with standards still forming. Using Boyd's OODA loop as a mental model, I'll walk the tools at each stage and the controls we found we needed: a fast System 1 gate, an identity for the agent, entitlements tuned to its actions, and delegated authority. You'll leave with six questions to test whether your architecture is agent-ready.