MCP 101 - Unlocking AI Superpowers with the Model Context Protocol

In this conversation, Jonny Daenen and Pierre Crochelet explore the Model Context Protocol (MCP), a framework that enhances AI assistants by allowing them to perform various tasks through tools, resources, and prompts.
They discuss the architecture of MCP, how to build an MCP server, and the developer flow for creating tools. The conversation also touches on the compatibility of MCP with different AI agents and the user experience, highlighting both the potential and limitations of the protocol.

👉 Link to the demo code: https://github.com/datamindedbe/demo-...
MCP servers: https://github.com/modelcontextprotoc... https://mcp.so/

Takeaways:

• MCP allows AI assistants to perform tasks beyond their initial capabilities.

• The architecture of MCP consists of a host, client, and server.

• Tools are the primary feature of MCP, enabling dynamic actions.

• Resources provide additional context for AI responses.

• Prompts are templates for common requests to the AI.

• Building your own MCP server is relatively straightforward with the right SDK.

• The developer flow includes creating tools and testing them easily.

• MCP is compatible with various AI agents, but implementation may vary.

• User experience with MCP is promising but still evolving.

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