Who it is for
Data analysts and engineers checking whether a table is sound before using or changing it.
AI Connectors · Data & Analytics
Governed data context: freshness, lineage, ownership and definitions
Overview
Decube holds governance context about data, and this connector puts it where the work happens instead of in a separate dashboard. The listing frames it as two audiences with different questions.
An analyst asks whether a table is current, complete or duplicated before reporting on it, and pulls the governed definition of a metric instead of reconstructing one. An engineer traces real upstream and downstream lineage before changing a schema, finds gaps in ownership, and writes context back. Automated checks can run in a CI pipeline through a pre-push hook, which moves the check earlier than review. The connector is community-listed.
Data analysts and engineers checking whether a table is sound before using or changing it.
Credentials gate the endpoint, so thirty-three is the listing's count. The listing describes reads for freshness, completeness, duplication, lineage and ownership, writes back into Decube, and automated checks run from a pre-push git hook.
Availability
Decube is listed in the Claude connectors directory only. Decube 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
Decube publishes 33 tools to Claude, deeper than 83.4% of the 1,253 Claude-listed connectors.
The median Claude-listed connector filed under Data & Analytics publishes 12, so this one runs 21 tools above its bucket's median and ranks 25th of 198 by tool count.
It falls in the 21-50 tools band, which holds 20% of the Claude directory.
Decube 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://connect.apac.decube.io/mcp Decube is community-listed in the Claude directory, the tier 770 of 1,253 connectors sit in (61.5%). It is the default for a self-published server, and says nothing either way about quality.
In the publisher's words
Decube MCP Server gives AI assistants direct, live access to governed context about your data, turning confident guesses into confidently right answers. Instead of asking a separate dashboard, teams query trusted context directly inside the tools they already use: Data Analysts can check whether a table is current, complete, or duplicated before reporting on it, and pull governed metric definitions on demand. Data Engineers can trace real upstream to downstream lineage before a schema change, find ownership gaps, write context back into Decube, and run automated checks in the CI pipeline via a pre-push git hook. Data Governance teams can run PII sweeps, check regulation compliance readiness (APRA, DORA, and similar regimes), and confirm every sensitive asset has an accountable owner, all without waiting on a manual audit cycle.
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
Governed SQL querying across warehouses with a BI layer attached
Claude
Metadata catalog and lineage context for ChatGPT queries
ChatGPT
Enterprise data context: search, lineage, ownership and governance
Claude
Read only access to Evidence reports and data
Claude · ChatGPT
Web pages and documents converted to structured data
ChatGPT
Document corpus parsing and search across 50-plus file types
Claude
This is an independent catalogue entry compiled by Node8 from Decube'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 Decube, 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.