How to Build (Custom) AI Agents with MCP

🤝 Your team not maximizing Claude? I run 1:1 and team AI workshops for companies doing $10M+ per year: https://aibuilder.academy/yt/w-Ml3NivoFo MCP is an easy way to give LLMs tools and context. Here, I walk through how to build a custom MCP server and use it to create a YouTube AI agent. 💻 Example Code: https://github.com/ShawhinT/yt-mcp-agent References [1] https://modelcontextprotocol.io/docs/getting-started/intro [2] https://github.com/cyanheads/model-context-protocol-resources/blob/main/guides/mcp-client-development-guide.md#1-introduction-to-mcp-clients [3] https://github.com/modelcontextprotocol/python-sdk Intro - 0:00 What is MCP? - 1:09 How MCP works - 2:56 MCP Client - 3:55 MCP Server - 5:20 Example: YouTube Agent via Custom MCP Server - 7:17 Step 1: Initialize MCP server - 9:02 Step 2: Add prompts and tools - 9:55 Step 3: Local transport -12:46 Step 4: Create agent - 13:00 Step 5: Interact with agent - 14:58