LinkedIn·Saturday, 8 August 2026·18d ago
We already have data catalogs. Why do we need MCP? When an AI agent is about to act on a dataset, it shoud answer 4 questions first: → Is…
Maarten Masschelein
CEO & Co-Founder @ Soda | Data and Context Management for AI
We already have data catalogs. Why do we need MCP?
When an AI agent is about to act on a dataset, it shoud answer 4 questions first:
→ Is this data covered by quality checks?
→ Who owns it?
→ Is there a contract that defines what good looks like?
→ Did the last scan pass?
A catalog stores some of these answers as documentation, written for humans to read. An agent needs them as a machine-readable response, at the moment of action.
That is what MCP (Model Context Protocol) changes.
It is the interface that lets AI agents ask these questions directly. Through the Soda MCP, an agent working in Claude or Cursor can check the state of a dataset before it builds on top of it.
The same data contract that tells your analyst the data is safe is the one the agent reads to decide whether to act.
This is the shift I keep coming back to: governance used to produce documentation. In the agentic era, governance has to produce answers software can consume.
Wiki pages do not stop an agent from acting on broken data. Executable contracts do.
If an AI agent asked your stack right now whether a dataset is safe to use, would it get an answer?
Btw we have an upcoming webinar on this topic next week where we will go over how to use Soda MCP !
https://lnkd.in/eFYj97tk
💬 2
View on LinkedIn Cross-referenced
Related on the wire
CLI, API, or MCP? Three ways to connect data quality to your stack, and most teams pick by habit rather than by the job. The question that…
You can do governance work in an afternoon that used to take months. Here are 3 things AI does for data quality that manual processes can't…
I am a data steward. How can I add AI into my workflow? Data stewards hold the business rules, but turning them into running checks…
Data analysts should not be the last line of defense for data quality. Yet that's where many teams end up. A data issue enters a pipeline…
Metadata is now growing beyond passive documentation. It has the potential to become "active". Active metadata is metadata that is…
MCPs have the potential to change data governance forever. Context is everything in data governance, and unfortunately for many teams its…