LoginSign Up
← Back to all sparks
M

MotherDuck

ANALYTICS
Velocity7.5

Serverless cloud data warehouse and analytics built on DuckDB

motherduck.com ↗

MotherDuck climbs from serverless DuckDB warehouse to an agent-operable data platform

data-warehouseduckdbmcpdata-pipelinesicebergembedded-analytics
◆Current state
MotherDuck ships a dense, real release stream on two fronts: tracking DuckDB core (1.5.x, DuckLake, concurrent checkpoints) and building an agent-and-embed layer on top (Dives data apps, an MCP server, the MCP Dive Viewer now in ChatGPT and Claude Cowork). The latest notes add server-side Iceberg interop and a new pipelines product, Flights.
◆Where it's heading
The product is moving up the stack from query engine toward a full data platform: pipelines (Flights), interactive apps (Dives, now GA), open-table-format interop (Iceberg, DuckLake), and broad connectivity via the Postgres endpoint (Looker, Retool, Drizzle, dbt Cloud, DBeaver). MCP-native access recurs throughout, treating AI agents as first-class users of the warehouse.
◆Prediction
Expect Flights and Iceberg attach to graduate from Preview to GA, more Postgres-endpoint BI and tool integrations, and continued MCP/agent surface. This is grounded in the visible pattern of previews maturing and steady Postgres-endpoint and MCP investment.

◆Recent moves

  1. 1d ago

    Server-side Iceberg attach and dbt Cloud support

    ⚡ SPARK

    Server-side Iceberg attach lets MotherDuck query external Apache Iceberg REST catalogs alongside its own and DuckLake tables, planting it firmly in open-table-format territory. Paired with direct dbt Cloud connectivity via the Postgres endpoint, it deepens the 'plug into the existing data stack' arc.

    View source ↗
  2. 8d ago

    DuckDB 1.4.5/1.5.4 support and Postgres endpoint BI compatibility

    DuckDB 1.4.5/1.5.4 support, Postgres-endpoint JDBC metadata fixes for BI tools like DBeaver and DataGrip, and on-demand REFRESH DATABASE for Dives on read replicas. Incremental work reinforcing both the DuckDB-parity and connectivity threads.

    View source ↗
  3. 23d ago

    Flights agent-native pipelines launch; Dives hit GA

    ⚡ SPARK

    Flights introduces agent-native data pipelines, a Python runtime for ingest, transformation, and replication managed via SQL, UI, or any MCP agent, while Dives reach GA and cloud coverage extends to Dublin. This is MotherDuck expanding from query engine toward an end-to-end, agent-operable data platform.

    View source ↗
  4. 1mo ago

    DuckDB 1.5.3, Retool native integration, compact Dive URLs

    DuckDB 1.5.3 support, a native Retool Cloud integration, and compact URLs for heavily-filtered Dives. Steady connectivity and Dives-usability gains along the established arc.

    View source ↗
  5. 1mo ago

    Looker connectivity, Obsidian plugin, and Dive embedding upgrades

    A broad bundle: Looker via the Postgres endpoint, an Obsidian plugin, TOON-encoded MCP responses, versioned Dive embeds, and the Dive Viewer as a ChatGPT app. Many small moves that widen both the BI-connectivity and MCP/embed surfaces.

    View source ↗
  6. 1mo ago

    SCIM provisioning and Dives per-session database overrides

    SCIM provisioning for enterprise identity, per-session database overrides and preconfigured state for embedded Dives, MCP data exports, and Claude Cowork rendering. Enterprise-readiness plus deeper Dives-embedding control.

    View source ↗