Loading video player...
Agentic AI makes model context protocol (MCP) easier than ever. In this video i break down how MCP works, why you should use it and how to use Claude Code to set it up for anything. Timestamps: 00:00 - Agents need real-world access (demo hook) 01:02 - What MCP means (USB-C of AI tools) 02:10 - MCP architecture: server, client, relay 03:05 - MCP tools vs resources (prompts mentioned) 04:05 - MCP vs APIs (intern vs professional analogy) 05:22 - Plug-and-play toolbox example 06:20 - IDE walkthrough + system design mindset 07:35 - Build overview: polling + diffing YouTube views 08:35 - Components: watcher, integrations, SQLite, observability -- Work with me: š¤ Ready to transform your business? Let's talk: https://bit.ly/3TinLo5 š Join the community ā https://bit.ly/4okIaaa š” Add me on LinkedIn - https://www.linkedin.com/in/mansel-scheffel/ [ABOUT ME] If you're new here ā Iām Mansel. In 2011, I left South Africa with nothing but a laptop and a digital piano. I taught myself IT, broke into cybersecurity in London, and built two consulting businesses ā one in cyber, one in cloud ā scaling solo to $52K+/month. Today, I run atomicOps, an AI consultancy based in New York where we help mid-market companies turn AI chaos into scalable systems as a transformation partner. I also help AI Automation Experts escape underpaid gigwork and build $25K+/month businesses using the same frameworks I used to scale mine.