Explore MotherDuck Data

Prerequisites

• An established MotherDuck connection (or an active MotherDuck MCP server)

Default Posture

• Start at the known catalog object; broaden to databases or shares only when the target is unknown.
• Use fully qualified table names once more than one database is attached.
• Check shared databases before concluding that data is unavailable.
• Use the MotherDuck MCP tools (list_databases, list_tables, list_columns, search_catalog) when available because they return structured results faster than ad hoc SQL.
• Before business-semantic exploration through MCP, call get_query_guide, then read only relevant root Guides and topic branches. Follow relatedGuides returned by catalog tools when they govern the objects in scope.
• Record whether a share is filtered and whether an existing Dive is Draft, Ready, Endorsed, or Archived; these attributes change what downstream agents should trust or expect to see.
• Return a concise schema map with table grain, join keys, date columns, and likely measures before moving into modeling or dashboard work.

Workflow