MotherDuck is launching Flights, an agent-native data pipeline that enables users to choose the MCP server and AI agent of their choice to build and deploy data pipelines in minutes using a flexible, general-purpose Python runtime.
According to the company, the combination of Flights and Dives in MotherDuck means that users can get from source data to answers in a single agent session–backed by serverless, sub-second analytics.
Ingesting data with Flights is powerful, and the use cases extend far beyond—run flexible transformations, call an LLM, replicate from an existing warehouse, ETL from SaaS APIs, and more, the company said.
Flights is currently in public preview.
Flights supports a growing list of agent-friendly interfaces while executing inside a general-purpose Python runtime. Flights are tightly integrated with MotherDuck databases—they connect the Python runtime to a users’ Ducklings (compute instances) using the DuckDB Python client.
Users can connect any MCP-capable agent (Claude, Cursor, ChatGPT, and more) to the MotherDuck MCP server and the agent gets the full Flights surface as tools: create, run, schedule, update, inspect logs, version, delete.
It also gets get_flight_guide, a built-in instruction set, so the same prompt produces a working Flight whether it's the agent's first or hundredth.
The MCP server is also the interface for creating Dives, so a single chat can take a raw source through ingestion and into a live dashboard or data app.
Every Flight operation has a matching SQL table function and anything that speaks SQL can manage Flights: a DuckDB client, BI tool, dbt, even another Flight.
Users can also manage Flights visually from within the MotherDuck UI, which includes the same tools as the SQL table functions: logging, run history, versions, environment variables, and the requirements.txt file for a Python environment.
For more information about this news, visit https://motherduck.com.