{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/054965b6bb4c466da7347cd6f2c4e2ae\" frameborder=\"0\" width=\"1664\" height=\"1248\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1248,"width":1664,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1248,"thumbnail_width":1664,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/054965b6bb4c466da7347cd6f2c4e2ae-8184e01ec725ca1b.gif","duration":5170.0874,"title":"Building Model Context Protocol Servers with FastMCP 🚀","description":"In this video, I walk you through writing model context protocol servers using FastMCP, which is quite similar to FastAPI and requires minimal code. We explore the concept of protocol servers as REST APIs, emphasizing their ability to handle requests for various tasks, like accessing weather data or booking flights. I also discuss the importance of tools, resources, and prompts within these protocols, and highlight the need for viewers to complete the homework of writing a client. Additionally, I touch on the potential risks associated with AI, particularly regarding agentic misalignment and memory poisoning. Please ensure you follow along and implement the steps I outline to set up your own MCP server."}