How AI Can Supercharge Data Teams: Real Example with MCP + Postgres
03.11.2025
•
Emil Krause & Jonny Daenen
See how AI agents can now talk directly to databases accelerating debugging, analysis, and development.
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. They discuss the setup of a database MCP server, demonstrate its capabilities in troubleshooting data inconsistencies, and highlight the importance of understanding data even when using advanced tools. The conversation also touches on the potential pitfalls of using such tools and the need for technical expertise in leveraging them effectively.
Try it out yourself: https://github.com/datamindedbe/demo-technology-exploration/tree/main/demos/postgres_mcp
Check out the MCP 101 video: https://www.youtube.com/watch?v=fIr55-koOJQ
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/winter-summer-school
Latest
AI Workflows in Agno: Building Deterministic Agents
Instead of letting a single agent roam freely across your data, Agno lets you build agents per data product.
Managing Airflow at Scale with Flowrs, a Rust-based Terminal UI
Flowrs is a Rust TUI for Apache Airflow that lets you manage all your environments from one terminal.
Arete: A Brainstorming Agent That Pushes Back
Arete is a structured brainstorm plugin for Claude Code that guides you through five phases before you write a single line of code
