Dataplex MCP server

other

In a large org, finding out which dataset or table actually has the data you need can eat an afternoon of asking around. Dataplex connected to Neotask turns that into a search: the agent browses Dataplex's Knowledge Catalog metadata to surface matching datasets, tables, and AI assets, along with lineage where it's tracked.

• Searches governed metadata instead of guessing which team owns a dataset
• Surfaces lineage and enriched metadata alongside basic search results
• Useful for both one-off discovery questions and ongoing data-governance reviews

What you can automate

Dataplex MCP server

Search and browse Google Cloud Dataplex (Knowledge Catalog) metadata to discover datasets, tables, and AI assets across an organization. Look up lineage and enriched metadata for governed data discovery.

Real workflows

Find the right dataset before building a report

Ask "is there an existing dataset with customer churn data?" and the agent searches Dataplex's catalog for matching assets, returning names, owners, and lineage so you're not duplicating an existing table.

Frequently asked questions

What does the Dataplex connection actually do?

Search and browse Google Cloud Dataplex (Knowledge Catalog) metadata to discover datasets, tables, and AI assets across an organization. Look up lineage and enriched metadata for governed data discovery.

Does this give me the data itself, or just where to find it?

It's for discovery — metadata, lineage, and asset location. Pulling the underlying data happens through whichever system hosts it.