18 minutesAWS re:Invent 2025 - Implementing Human-in-the-Loop Controls for Multi-Agent AI Systems (CNS428)
See how approval gates can be implemented as explicit workflow checkpoints rather than informal manual review after something goes wrong.
Anthropic. The protocol's designers — Theo Chu, David Soria Parra and Alex Albert — walking through why MCP exists, the components (server, client, transport), the reception since the November 2024 release, and which servers they actually use day-to-day. Useful as the canonical source after the Nate Herk overview.
This is canonical context, not a complete production guide. Protocol details are useful, but deployment security, auth, network exposure and tool permissions still need current documentation review.
Understand the protocol roles: host, client, server, tools, resources, prompts and transports.
Watch or read a plain-language MCP overview first if protocol terms are new.
Last reviewed: May 18, 2026
Continue through the same learning path with the next curated companion videos.
18 minutesSee how approval gates can be implemented as explicit workflow checkpoints rather than informal manual review after something goes wrong.
4 minutesUnderstand why multilingual embeddings matter for private internal search and where local retrieval can reduce data-exposure risk.
17 minutesSet up a multi-agent coding workflow with explicit review boundaries so generated changes stay small, tested and owned.