Loading video player...
Emil Krause & Jonny Daenen explore how to accelerate dbt development by integrating MCP (Model Context Protocol) with Postgres and Cursor. Emil demonstrates how to solve a database bug by allowing AI agents to interact directly with databases and his code. Even though this approach is very effective, it remains important to understand the data, even when using advanced tools. Try it out yourself: https://github.com/datamindedbe/demo-technology-exploration Check out our MCP 101: https://www.youtube.com/watch?v=fIr55-koOJQ ------------------------------ To stay up to speed in the world of data, subscribe to our channel: https://www.youtube.com/channel/UCxi05zIoV9bm69OAUmRoUDQ?sub_confirmation=1 Want to elevate your Data Engineering skills? Join our upcoming Data Engineering Winter School 2026 in Leuven, running February 2–6, 2026. A 5-day, hands-on program designed and taught by seasoned Dataminded data engineers, combining practical workshops with online preparation videos. ✅ Taught in English ✅ 15% Early Bird Discount until December 30th ✅ KMO-portefeuille eligible 👉 Learn more and register: https://www.dataminded.com/academy Chapters 00:00 Introduction to MCP and Postgres Integration 00:41 Exploring the MCP Server Functionality 02:20 Real-World Application: Debugging Salary Percentiles 06:29 Creating and Testing DBT Models 07:11 Benefits and Dangers of AI Assistance 09:42 Setting up your own postgres MCP in Cursor 11:08 Out-of-the-box MCP Solutions 11:44 Setting Up MCP Servers in Cursor 12:57 Challenges & Pittfals 14:54 Comparing MCP with Other Tools 16:15 MCP vs Semantic Models 17:16 Other development tasks 18:39 Claude Desktop vs Cursor 19:59 Summary #dataengineering #mcp #cursorai #cursor