Adobe Customer Journey Analytics
Run cross-channel reports and build segments in Adobe Customer Journey Analytics.
Search your data catalogue, trace column-level lineage, draft SQL and edit governance metadata.
Opens Agent Studio, where connecting is one click. The connector URL below works in any MCP client.
Paste it into any MCP client. Setup docs
The DataHub MCP server connects your data catalogue to Claude, ChatGPT and any MCP-compatible agent. It exposes 34 tools for searching datasets and dashboards, tracing table and column-level lineage, drafting SQL from real usage, and editing governance metadata — tags, glossary terms, owners, domains and descriptions. Sign-in is OAuth against DataHub Cloud, and the connector writes as well as reads.
Verified connector
Listed by Anthropic as a partner connector in its Connectors Directory.
Connection checked by Agentman on .
Anthropic states this reflects the level of review a connector received, not a security audit.
Tool names from Anthropic's directory listing. This server requires sign-in, so we could not read tool descriptions or parameter schemas.
datahub:account, with no read/write split. The consent screen offers nothing to decline, and unlike ChartMogul's equally coarse scope this one gates writes. Access control lives entirely in DataHub's role and policy model.accept_or_reject_proposals lets an agent complete a human review step. DataHub's change proposals workflow exists so owners and stewards approve suggestions; an agent with Editor or Admin privileges can approve them instead. Connect as a Reader if you want the propose-only path.readOnlyHint, destructiveHint and idempotentHint; the repository sets only readOnlyHint, so the writing half of the surface is unlabelled in clients that read those fields. We could not read the hosted server's annotations.TOOLS_IS_MUTATION_ENABLED=false disables writes in the open-source server. DataHub documents no equivalent tenant-level toggle for the Cloud endpoint; the Cloud controls are roles, policies and scoped servers.Your privileges are most likely not configured correctly. DataHub's change proposals guide gives exactly this answer, and directs admins to Settings then Permissions to edit the roles and policies so the account holds the review privileges the same page lists. Proposal visibility follows privileges, not the connector.
The endpoint at mcp.datahub.com is DataHub Cloud only. DataHub's guide marks the managed MCP server as available on DataHub Cloud v0.3.12 and later, with OAuth added in v1.0.2 and later. DataHub Core users self-host the open-source server from the acryldata/mcp-server-datahub repository instead.
Yes, if the signed-in account holds the review privileges. The connector lists accept_or_reject_proposals, and DataHub's change proposals guide reserves review to the Manage Tag Proposals, Manage Glossary Term Proposals and related privileges, granted by default to the Editor and Admin roles. Connect as a Reader to remove that ability.
The prior values are retained, but no tool restores them. DataHub's aspect versioning design keeps every earlier version of an aspect as an audit trail under version 0 semantics. The 34-name connector listing contains no restore, revert or undo verb, so recovery happens outside the connector.
Editor or Admin. DataHub's roles guide defines Reader as able to read all metadata and unable to edit anything by default, Editor as able to read and edit all metadata without administrative actions, and Admin as able to do everything. Tokens are scoped to the signed-in user.
Connect with a Reader-role account or a scoped service account. DataHub documents a Reader role that cannot edit by default, and service accounts that carry their own role plus an optional Default View restricting which assets the MCP server can search. Both narrow the connection without touching OAuth.
.md suffix) · retrieved 2026-08-18readOnlyHint annotation, the TOOLS_IS_MUTATION_ENABLED gate and the absence of glossary, lifecycle and proposal tools — at commit 3c2d18cb87dab223568610651fc8b91dfab27a8e, dated 2026-08-13 (cloned 2026-08-18; the repository URL is a link published on DataHub's own MCP guide) · retrieved 2026-08-13https://mcp.datahub.com/mcp — anonymous initialize returned HTTP 401 with WWW-Authenticate: Bearer resource_metadata="https://mcp.datahub.com/.well-known/oauth-protected-resource"; the protected-resource descriptor returned HTTP 200 advertising scopes openid and datahub:account with authorization_servers of https://mcp.datahub.com/mcp; the authorization-server metadata returned HTTP 200 at both /.well-known/oauth-authorization-server and /.well-known/oauth-authorization-server/mcp with identical content (2026-08-18) · retrieved 2026-08-18docs.datahub.com/robots.txt returns HTTP 404 with a Docusaurus 404 shell, so the host publishes no crawl directives and no Content-Signal; datahub.com/robots.txt returns HTTP 200 disallowing only /wp-admin/, /wp-login.php, /slack/ and /?s=, with no Content-Signal line. docs.datahub.com/llms.txt returns a genuine machine-readable index, and appending .md to a docs URL returns real Markdown (all checked 2026-08-18) · retrieved 2026-08-18Connect DataHub once and your agents call these tools on their own: on a schedule, in a workflow, with nobody at the keyboard.