Keynote at MCP Dev Summit Toronto 2026
Governing MCP for a Workforce the Size of a City
Deploying the Model Context Protocol across a workforce of about 750,000 people, and what governing that actually requires: a registry, a gateway, an AI gateway, and a rollout that can say no.
- When
- Tuesday 6 October 2026, 9:59 AM to 10:14 AM EDT
- Where
- Ballroom East/Center, The Conference Centre at the University of Toronto, 89 Chestnut Street, Toronto
The talk
"How many users do we need to support on MCP?" "Possibly all of them. Maybe 750,000." That was the start of a conversation about deploying MCP at a scale matching frontier SaaS services. Our demo was amazing: one minute, one agent, one tool, MCP in between. Then came the real engineering. Nobody had really said yes to any of it. There was also nowhere to say no.
That exposed us to the world this session covers: a registry as the source of truth for which servers exist, who owns them, and what an agent may discover. A gateway as the single path between agents and tools: identity, authorization, rate limiting, and policy enforced once instead of rebuilt per server. An AI gateway as the governed route to inference. Then the rollout: phased, control plane in GitOps, admission control so an unsanctioned server can't land, runtime detection on the tool-execution surface, and workload identity so the gateway knows which agent is calling.
We close on what the gateway caught, what slipped past us, how we handled scale and security, and everything on the road to 200,000 deployed internal users at a single company. We counted. The number was horrifying.
The abstract as published on the event schedule. Two dashes in the original are set as a colon here.
The speaker
Michael Rishi Forrester is a generative AI strategist with nearly 30 years in technical leadership, workforce transformation, and artificial intelligence. He is the AI Workforce Transformation Lead at Accenture LearnVantage, where he works on Claude and generative AI adoption with governments and forward deployed engineers. He has trained more than a million engineers through every major platform shift, wrote Agentic DevOps with Claude Code (Packt, 2026), and authored the Agentic Covenants, a framework for AI agent safety. He speaks regularly at AI Engineer World's Fair, Linux Foundation AI Con, and MCP Con. His work centers on Claude and its ecosystem, specifically Claude Code, enterprise AI governance and adoption, and closing the gap between what executives expect from AI and what AI can actually deliver. His view is that the biggest blocker to AI adoption is people and process, not which model you use, but he will still wax poetic about Context Rot and other technical concepts if you let him.