Why it matters
AI Engineer session on Remote MCPs: What we learned from shipping, presented by John Welsh, Anthropic. It adds practical context for how teams are building and operating AI systems in production.
My takeaway: Remote MCPs: What we learned from shipping — John Welsh, Anthropic is an agent-security signal. The practical read is that autonomy, memory, tool permissions, and third-party integrations are the control surface that needs threat modeling and monitoring.