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.
Anthropic’s own published signals, snapshot of August 5, 2026; units undocumented — treat as ordinal.
Over time
Details
Tools(34)
- accept_or_reject_proposals
- add_owners
- add_related_terms
- add_structured_properties
- add_tags
- add_terms
- compare_glossary_term_versions
- create_glossary_term
- create_glossary_term_version
- draft_sql_for_tables
- get_dataset_queries
- get_entities
- get_glossary_term_versions
- get_lineage
- get_lineage_paths_between
- get_me
- grep_documents
- list_lifecycle_stages
- list_pending_proposals
- list_schema_fields
- note_metadata_observation
- propose_create_glossary_term
- propose_lifecycle_stage
- remove_domains
- remove_owners
- remove_structured_properties
- remove_tags
- remove_terms
- save_document
- search
- search_documents
- set_domains
- set_lifecycle_stage
- update_description
Data from Claude’s public directory API, snapshotted daily by the MCP App Tracker. A listing describes what the directory publishes — not an endorsement.