Who it is for
Teams with data in MotherDuck who need answers without writing the queries themselves.
Overview
MotherDuck Corporation connects an assistant to a MotherDuck data warehouse so that exploring, analyzing, and managing stored data happens through plain questions instead of hand-written SQL.
The app is built to run against tables as they already are. No semantic layer or preparatory modeling step is expected before a question is asked. In practice the assistant works the way an analyst does: it explores what is available, validates what it finds, analyzes it, and circles back as the question sharpens.
Answers can be captured as Dives, which are interactive visualizations that persist and can be passed to colleagues. A saved Dive keeps reflecting current warehouse data rather than freezing the numbers from the moment it was made.
Teams with data in MotherDuck who need answers without writing the queries themselves.
Saved Dives stay bound to live warehouse data, so a shared visualization keeps updating instead of becoming a snapshot.
Availability
MotherDuck Corporation ships this on both marketplaces: MotherDuck is listed in the Claude connectors directory and in the ChatGPT apps directory, under the same publisher domain.
Only 392 of the 3,150 products in this directory are listed in both marketplaces. One MCP server can serve both surfaces; what differs is each platform's listing and review process.
ChatGPT listing
Claude listing
MotherDuck publishes 15 tools to Claude. That is a mid-sized surface: 59.4% of the 1,253 Claude-listed connectors expose fewer.
The median Claude-listed connector filed under Data & Analytics publishes 12, so this one runs 3 tools above its bucket's median and ranks 70th of 198 by tool count.
It falls in the 11-20 tools band, which holds 22.5% of the Claude directory.
MotherDuck publishes a remote MCP endpoint. Claude connects to it over HTTP; there is nothing to install locally.
Every connector in the Claude directory is remote, all 1,253 of them, so transport is not a differentiator there.
https://api.motherduck.com/mcp MotherDuck carries partner verification in the Claude directory, which 474 of 1,253 listings do (37.8%). That is a review step past self-publishing, not an Anthropic-built server.
In the publisher's words
Connect AI assistants to your MotherDuck data warehouse. Explore, visualize, and manage data using natural language–no SQL skills required. Create Dives: interactive visualizations that let you save and share answers with your team, staying up-to-date with your latest data. Works with real-world data without requiring semantic models or pre-configuration. Your AI assistant acts like a data analyst, exploring, validating, analyzing, and visualizing data iteratively to answer your questions.
Quoted from the connector's own Claude directory listing as captured in August 2026. Node8 did not write it and does not vouch for it.
Nearby
Customer feedback analysis across support and sales channels
Claude · ChatGPT
Dashboard metrics from Geckoboard, queried in conversation
Claude
One analytics agent over a connected SQL warehouse
Claude
Governed warehouse questions through a Wren AI semantic layer
Claude
Search and reference documents stored in Box
Claude · ChatGPT
AI visibility and GEO metrics from a Brandi AI instance
Claude
This is an independent catalogue entry compiled by Node8 from MotherDuck's public marketplace listings as they stood in August 2026. Listing facts come from the marketplaces; the comparisons against the rest of the directory and any live-endpoint measurements are Node8's. Node8 is not affiliated with MotherDuck Corporation, and inclusion here is not an endorsement.
Node8 builds MCP servers end to end: deciding which tools are worth exposing, the authentication and permission model, the review submissions, and the onboarding that gets them used. One server serves ChatGPT, Claude, and Microsoft Copilot.