DataHub

DataHub's MCP server gives AI agents the enterprise context they need to work with your data. Surface curated knowledge — runbooks, FAQs, business definitions, and vocabularies — so agents operate with the same shared understanding as your teams. Search across datasets, dashboards, and pipelines, then pull ownership, governance policies, quality signals, and documentation to understand what you're looking at. Trace lineage at the table and column level. Surface real SQL queries to see how data is actually used. Apply tags, glossary terms, owners, and descriptions at scale. The context layer that makes AI agents enterprise-ready.

You can use DataHub to:

Find and understand a dataset:
"Search DataHub for our customer_orders table, show me its owners, documentation, and current data quality status."

Trace column lineage:
"Trace the upstream lineage of revenue_usd in the finance.monthly_summary table back to its source systems."

Govern at scale:
"Find all datasets tagged 'pii' that are missing an owner and add the data-platform team as owner."

See real usage:
"Show me the most common SQL queries that hit the events.page_views dataset in the last 30 days."