Who it is for
Data teams querying an Iceberg, Parquet or Delta lakehouse governed by Dremio.
AI Connectors · Data & Analytics
Query lakehouse data through Dremio's semantic layer and access controls
Overview
Dremio puts a semantic layer over lakehouse storage, and this connector routes an agent through it rather than around it. The consequence the listing emphasises is access: fine-grained controls, row-level and column-level security, and shared business definitions apply to the agent exactly as they apply to a user, so an agent sees only what its identity is entitled to.
Queries execute directly against data in the lakehouse, covering Iceberg, Parquet and Delta, with no copy or movement step. This connector carries the partner tier, meaning it passed a review step rather than being self-published, and Dremio publishes documentation.
Data teams querying an Iceberg, Parquet or Delta lakehouse governed by Dremio.
No endpoint URL appears in the listing, so nothing could be connected to and seven is Dremio's published count. The listing describes the surface as queries running through the same semantic layer and permissions a person would use.
Availability
Dremio Cloud is listed in the Claude connectors directory only. Dremio, Inc has no app under the same domain in the ChatGPT directory; 392 of the 3,150 products here are on both marketplaces, and this is not one of them.
The MCP server behind a Claude connector is usually the same server a ChatGPT app would need, so the absence is a distribution decision rather than a technical one.
Claude listing
Dremio Cloud publishes 7 tools to Claude. That is a mid-sized surface: 33.4% of the 1,253 Claude-listed connectors expose fewer.
The median Claude-listed connector filed under Data & Analytics publishes 12, so this one sits 5 tools below its bucket's median, 129th of 198.
It falls in the 7-10 tools band, which holds 14.6% of the Claude directory.
Dremio Cloud's Claude listing does not publish an endpoint URL. 48 of the 1,253 Claude listings are in the same position: real listings with documentation but no URL in the directory record, so the endpoint has to come from the publisher's own docs.
Every connector in the Claude directory is remote, all 1,253 of them, so transport is not a differentiator there.
Dremio Cloud 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
Dremio provides a Model Context Protocol (MCP) server that allows AI agents to securely access, query, and reason over enterprise lakehouse data through Dremio's unified semantic layer. With Dremio's MCP offering, agents interact with data exactly as users do in Dremio—respecting fine-grained access controls, row- and column-level security, and shared business definitions. Queries are executed directly on data in your lakehouse (Iceberg, Parquet, Delta), with no data duplication or movement. Dremio's MCP server ensures that AI agents see only what they're authorized to see, while benefiting from the same semantic consistency and performance that teams rely on for analytics and BI.
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
Materials characterisation data, notebooks, and instrument streams
Claude
Search and reference documents stored in Box
Claude · ChatGPT
Ecommerce customer analytics: cohorts, baskets and segment profiles
Claude
NPS, CSAT and CES across feedback channels with the verbatims behind them
Claude
BigQuery dataset discovery and SQL execution, published by Google
Claude
Social and paid social performance analysis over a content library
Claude
This is an independent catalogue entry compiled by Node8 from Dremio Cloud's public marketplace listing as it 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 Dremio, Inc, 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.