Is this an official DataHub MCP server?

No. It is Memtro's MCP server with Memtro's DataHub connector behind it: the connector reads DataHub through its API with the credentials you connect on Dashboard → Connections, and DataHub publishes nothing here. The same endpoint carries every other system you connect and Memtro's memory tools.

Nothing on top of Memtro. One price per organisation by its number of users, from $50 a month for up to 10 users after a 7-day free trial, with every connector, the MCP server, jobs and memory included. You bring your own model keys.

Can it change anything in DataHub?

Only when you ask, and only what it has been granted: raise an incident on a data asset; change an incident's state or stage (for example resolve it); add a tag to an asset or column; remove a tag from an asset or column; add a glossary term to an asset or column; remove a glossary term from an asset or column; add an owner to an asset; remove an owner from an asset; add a link to an asset; remove a link from an asset; edit the description of a dataset column or a container; set an asset's domain; clear an asset's domain; mark an asset deprecated, or not. Every other tool reads, searches or lists. An administrator grants each acting tool by name per team, and a personal connection acts only after its owner allows it.

Any MCP client that speaks Streamable HTTP: Claude Code, Cursor, Claude Desktop, OpenCode, Codex, Zed, Windsurf, Cline and the Anthropic and OpenAI SDKs. There is no local process to run; the server is remote and authenticated with your key.

MCP server · Databases and warehouses

DataHub MCP server

DataHub in any MCP client, through Memtro: DataHub does not publish this server. Memtro's DataHub connector reads DataHub through its API with the credentials you connect, and one endpoint hands those tools, every other system you connect and Memtro's memory tools to Claude Code, Cursor, Claude Desktop or anything else that speaks Streamable HTTP, as you.

What the model can do

DataHub metadata catalogue: search datasets, dashboards, charts, pipelines, glossary terms, tags and domains, a dataset's owners, tags, terms, domain, deprecation, health and links, upstream and downstream lineage, and incidents; when you ask, can raise and resolve incidents, add or remove tags, glossary terms, owners and links, edit column or container descriptions, set or clear a domain, and mark assets deprecated.

Reads

datahub_searchSearches the DataHub catalogue: datasets, dashboards, charts, pipelines (data flows), tasks (data jobs), containers, glossary terms…
datahub_datasetOne DataHub dataset: name, platform, description, owners (by urn, groups by name) and ownership type, tags, glossary terms, domain, deprecation…
datahub_lineageWhat a DataHub asset depends on (UPSTREAM) or what depends on it (DOWNSTREAM), across hops: urn, type, name, platform and how many hops away.
datahub_incidentsIncidents on a DataHub dataset, data job, pipeline, dashboard or chart: type, title, description, priority, state (ACTIVE or RESOLVED)…

Acts, when you ask

These change something in DataHub. The model is told to use them only when you ask for exactly that, and each one is granted by name: per team on a shared connection, by the owner on a personal one.

datahub_raise_incidentRaises an incident on a DataHub asset: it shows as unhealthy to everyone who views it and its downstream users…
datahub_update_incidentChanges a DataHub incident's state (ACTIVE or RESOLVED) and stage, with an optional message everyone viewing it sees…
datahub_add_tagAdds a tag (by its urn, urn:li:tag:…) to a DataHub asset, or to one column of a dataset.
datahub_remove_tagRemoves a tag from a DataHub asset or one column of a dataset.
datahub_add_termAttaches a glossary term (urn:li:glossaryTerm:…) to a DataHub asset or one column of a dataset.
datahub_remove_termRemoves a glossary term from a DataHub asset or one column of a dataset.
datahub_add_ownerMakes a DataHub user (urn:li:corpuser:…) or group (urn:li:corpGroup:…) an owner of an asset, optionally with an ownership type urn…
datahub_remove_ownerRemoves a user or group as an owner of a DataHub asset (of one ownership type when given).
datahub_add_linkAdds a documentation link (a URL with a label) to a DataHub asset, shown to everyone viewing it.
datahub_remove_linkRemoves a documentation link from a DataHub asset, identified by its URL (and label, when two links share a URL).
datahub_update_descriptionReplaces the documentation of one column of a DataHub dataset (give field) or of a container (a container urn, no field).
datahub_set_domainPuts a DataHub dataset, chart, dashboard, pipeline or task into a domain (urn:li:domain:…), replacing any domain it had.
datahub_unset_domainRemoves a DataHub asset from its domain.
datahub_update_deprecationMarks a DataHub asset deprecated (with a note and an optional decommission date) or no longer deprecated…

Connect it

First connect DataHub on Dashboard → Connections, then add Memtro to your client once. The DataHub tools appear alongside the tools of everything else you have connected; nothing is configured per connector.

Claude Code

The Memtro plugin registers the server and a skill for when to use it; the tools are then available in every session.

claude plugin marketplace add memtro-org/claude-memtro
claude plugin install memtro@memtro --config api_key=sk-memtro-...

Cursor

Add the server to .cursor/mcp.json in the project, or to the global file under ~/.cursor/.

{
  "mcpServers": {
    "memtro": {
      "url": "https://platform.memtro.com/api/mcp",
      "headers": {
        "Authorization": "Bearer sk-memtro-..."
      }
    }
  }
}

Claude Desktop

Create a personal API key on Dashboard → Profile → API keys. In Claude Desktop add an MCP server of type HTTP with URL https://platform.memtro.com/api/mcp and the header Authorization: Bearer sk-memtro-…

OpenCode

A remote server in opencode.json.

{
  "mcp": {
    "memtro": {
      "type": "remote",
      "url": "https://platform.memtro.com/api/mcp",
      "headers": {
        "Authorization": "Bearer sk-memtro-..."
      }
    }
  }
}

Pi

One command: pi mcp add memtro --url https://platform.memtro.com/api/mcp --bearer-token-env-var MEMTRO_API_KEY. Tools arrive as mcp__memtro__*. The pi-memtro extension registers it for you, alongside Memtro as the model.

Any other client

Add an MCP server of type HTTP (Streamable HTTP, stateless) at https://platform.memtro.com/api/mcp with the header Authorization: Bearer sk-memtro-.... Codex, Zed, Windsurf, Cline and the SDKs all take a remote server this way.

Who may use it

The key identifies the person, and the server offers that person the tools they may use everywhere else in Memtro. A shared DataHub connection is used by the teams an administrator granted it to, tool by tool, on the Permissions page; a personal connection is used by its owner alone, and its tools that act stay off until the owner allows them. See Teams and permissions and Connectors.

Ask it like this

› What depends on the orders table in DataHub?
› Who owns the customer_events dataset?
› Which datasets are tagged PII in the finance domain?
› Are there any active incidents on the revenue dashboard?
› Mark the legacy_orders table deprecated with a note to use orders instead.

Questions

Is this an official DataHub MCP server?: No. It is Memtro's MCP server with Memtro's DataHub connector behind it: the connector reads DataHub through its API with the credentials you connect on Dashboard → Connections, and DataHub publishes nothing here. The same endpoint carries every other system you connect and Memtro's memory tools.
What does it cost?: Nothing on top of Memtro. One price per organisation by its number of users, from $50 a month for up to 10 users after a 7-day free trial, with every connector, the MCP server, jobs and memory included. You bring your own model keys.
Can it change anything in DataHub?: Only when you ask, and only what it has been granted: raise an incident on a data asset; change an incident's state or stage (for example resolve it); add a tag to an asset or column; remove a tag from an asset or column; add a glossary term to an asset or column; remove a glossary term from an asset or column; add an owner to an asset; remove an owner from an asset; add a link to an asset; remove a link from an asset; edit the description of a dataset column or a container; set an asset's domain; clear an asset's domain; mark an asset deprecated, or not. Every other tool reads, searches or lists. An administrator grants each acting tool by name per team, and a personal connection acts only after its owner allows it.
Which clients work?: Any MCP client that speaks Streamable HTTP: Claude Code, Cursor, Claude Desktop, OpenCode, Codex, Zed, Windsurf, Cline and the Anthropic and OpenAI SDKs. There is no local process to run; the server is remote and authenticated with your key.