> ## Documentation Index
> Fetch the complete documentation index at: https://honeydew.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# DataHub

[DataHub](https://datahub.com/) is a metadata platform. It catalogs the data assets
across your stack — along with their lineage, ownership, and glossary terms — and
stores the context pages that document them.

Honeydew's AI can read those context pages as
[context](#datahub-as-a-context-source) when answering questions.

<Info>
  This integration is in Beta. To enable for your organization,
  please contact [support@honeydew.ai](mailto:support@honeydew.ai).
</Info>

## Two Context Layers

Honeydew and DataHub cover different levels of the stack:

|                 | Honeydew [Context Layer](/docs/integration/context-layer/overview)                  | DataHub                                                                    |
| --------------- | ------------------------------------------------------------------------------ | -------------------------------------------------------------------------- |
| **Grounded in** | The semantic layer — governed metrics, entities, and calculations              | The catalog — assets, lineage, ownership, and glossary terms               |
| **Scope**       | How your organization analyzes: methodologies, conventions, and past decisions | What exists across the data estate, where it came from, and who governs it |
| **Answers**     | How a number is defined and computed correctly                                 | What an asset is, how it is used, and whether it is trusted                |

The two are complementary. DataHub describes the assets and documents them in
context pages; Honeydew defines the logic that turns them into governed metrics,
and generates the SQL. Reading DataHub context pages into Honeydew avoids
restating business knowledge that is already written down in the catalog.

## DataHub as a Context Source

DataHub is supported as an
[External Knowledge](/docs/integration/context-layer/context-management#external-knowledge)
source, so the AI can fetch context pages from DataHub over MCP.

Context pages are the documents DataHub stores alongside the catalog — knowledge
articles, runbooks, decisions, and FAQs. They are the DataHub equivalent of a
Notion or Confluence page: prose written for readers, rather than catalog
metadata about an asset.

Use this to reuse business knowledge that DataHub already governs, instead of
restating it as Honeydew context. Definitions stay owned in one place, and
Honeydew reads the current version at query time.

### Setup

1. Go to **Settings** → **MCP connections** and connect **DataHub**. Honeydew
   connects to DataHub Cloud's hosted MCP server at `https://mcp.datahub.com/mcp`
   over OAuth. Each user authenticates individually, so content is fetched with
   their own permissions.
2. Create an External Knowledge context item whose `external_source.tool` is
   `mcp__datahub__search_documents` and whose `resource_id` is the URN of the
   context page to fetch.

<Tip>
  A context page URN has the form `urn:li:document:<id>`. Copy it from the page in
  DataHub.
</Tip>

DataHub also exposes `mcp__datahub__grep_documents`, which searches within
context page content using a regular expression.

See [External Knowledge](/docs/integration/context-layer/context-management#external-knowledge)
for the full field reference.

<Note>
  Publishing Honeydew semantic definitions into DataHub is not supported yet.
  Reach out to [support@honeydew.ai](mailto:support@honeydew.ai) if you need it.
</Note>