DataHub MCP Server

Official MCP server for searching and inspecting DataHub metadata, lineage, and trust signals from an AI client.

Description

The DataHub MCP Server is Acryl Data's official Model Context Protocol server for DataHub. DataHub is a metadata and data-catalog system: it gathers technical and organizational context about data assets, including tables, columns, dashboards, pipelines, documents, and ML models. The MCP Server gives a compatible AI client access to the metadata present in DataHub. It is not a general database-access layer and not an execution environment for arbitrary SQL against Snowflake, Postgres, or a warehouse. Its role is discovery, interpretation, and governance context; an agent can draft SQL from that context, but execution requires a separately authorized database connection or another tool.

What the server finds and explains, according to the provider

The official README describes natural-language search across the DataHub landscape. It can help find relevant tables, columns, dashboards, and metrics when those entities and their metadata have been cataloged in the organization's DataHub instance. Results can be narrowed with structured expressions, filters, and sorting; the source lists wildcards, tag field searches, and Boolean logic. For a discovered entity, an agent can retrieve details, schema fields, ownership, documentation, tags, glossary terms, usage, and quality information. That is a catalog query, not a read of a table's raw rows.

For result assessment, DataHub names trust signals such as popularity, quality, lineage, and query history. These signals can help an agent rank or interpret a result, but they do not replace business approval or establish correctness on their own. Their value depends on the metadata, quality information, and usage history the organization has actually maintained in DataHub. The server can also surface real SQL queries referenced for a dataset or column in DataHub, helping an agent understand join patterns, filters, and aggregations. Query history can expose business logic or sensitive identifiers, so it must be included in the access model.

Lineage, dashboards, and columns in context

According to the repository, get_lineage and get_lineage_paths_between retrieve upstream and downstream lineage for entities such as datasets, columns, and dashboards, with hop control, filters, and paths between assets. This can help assess which downstream objects may be affected before a planned change. Official documentation describes lineage at table and column level; it does not guarantee that every connected source supplies complete or accurate lineage. Validate high-impact conclusions with the catalog and the responsible teams.

search, get_entities, and list_schema_fields support discovery and inspection. The server can also search saved documents when the catalog includes them; the README says document tools are hidden when no documents exist. This lets an agent consider tables, columns, dashboards, metrics, and their business terms in shared context. It fits data analysis and research because it makes existing data assets discoverable and understandable, rather than bypassing source-system access controls.

Deployment and authentication

For DataHub Cloud, there is a managed MCP endpoint; the documentation recommends OAuth with Dynamic Client Registration for interactive clients. Tokens are tied to the signed-in DataHub user. For service accounts, unattended workflows, DataHub Core, or clients without remote OAuth support, the documentation names personal access tokens. The open-source server can run locally over stdio with uvx mcp-server-datahub or be self-hosted. Local stdio reads DATAHUB_GMS_URL and DATAHUB_GMS_TOKEN from the environment or from ~/.datahubenv.

For a shared HTTP deployment, the current source requires each request to carry its own bearer token. A server-wide DATAHUB_GMS_TOKEN is deliberately refused so that permissions and audit identity remain per user. Tokens belong only in the Authorization header, never in URLs. The DataHub instance must enable metadata-service authentication so it can identify the caller. The /health endpoint reports process health only and does not contact DataHub.

Permissions, metadata exposure, and the model path

The MCP Server can return only information that the selected DataHub token and DataHub policies make visible. Even read-only catalog access can be sensitive: table and column names, classifications such as PII, owners, query history, dashboards, documents, and lineage can reveal architecture, business processes, or data flows. Use a minimally privileged account for each agent. For service accounts, the documentation says a Default View can scope search to specific domains, platforms, or a team's assets.

Read-only tools do not change catalog state. Mutation tools for tags, glossary terms, owners, domains, descriptions, and structured properties are disabled by default and require TOOLS_IS_MUTATION_ENABLED=true; compatible clients can use MCP hints to request confirmation. Enable them only for narrowly defined workflows and review change-proposal processes. The server handles tool calls, but returned results may enter the connected AI client's context. Depending on client, model provider, prompt, logging, and retention, returned metadata can travel to an external model path. Review data classification, contractual terms, and client controls; never place secrets in prompts, screenshots, or repositories.

License, limits, and positioning

The acryldata/mcp-server-datahub repository is licensed under Apache-2.0. On 2026-09-08, the GitHub API reported exactly 80 stars; this is a point-in-time repository-popularity signal, not evidence of quality or security. The server is open source, while availability of DataHub Cloud, DataHub Core, self-hosted infrastructure, and the selected AI client depends on the chosen deployment. The provider publishes current terms. Data Analysis and Research fit because the server makes metadata discoverable, comparable, and usable for data questions without replacing database access itself.

FAQ

Does the DataHub MCP Server read table rows? No. According to the documentation, it returns DataHub metadata such as assets, schemas, lineage, query context, and governance information. It can draft SQL using that context; execution requires a distinct, explicitly authorized database path.

Can an agent change metadata? Only when mutation tools have been deliberately enabled through the named environment variable and the DataHub account is authorized. For research and analysis, read-only tools should remain the default.

How can I limit visibility? Use a dedicated minimally privileged user or service account. Add a Default View for service accounts and review DataHub policies before connecting the agent to an externally hosted model.

Requirements

DataHub Cloud or DataHub Core, a personal access token or OAuth login, an MCP-capable client, and uv/uvx for local operation.

Installation instructions

The DataHub MCP Server makes metadata from your DataHub catalog available to an MCP-capable AI client. Start with a clear objective: find data assets, understand columns, review dashboard and metric context, or assess change impact through lineage. The server is not a direct database connector. It returns catalog context; SQL execution belongs only in a separate, explicitly approved database workflow.

Step 1: Define visibility before connecting

First determine which DataHub entities the agent truly needs to see. Table and column names, PII tags, ownership, glossary terms, query history, documents, and lineage can already be sensitive. Create a dedicated DataHub user or service account for the agent with minimal rights. For a service account, a Default View can, according to the official documentation, scope search to particular domains, platforms, or assets. Test that restriction with a search for a known asset before allowing the account to expose production metadata to an AI client.

Step 2: Connect DataHub Cloud with OAuth

For an interactive client, the official universal endpoint https://mcp.datahub.com/mcp is the recommended starting point. On first connection, the client asks for your DataHub domain and then guides you through OAuth login. The login can use the SSO configuration of your tenant. The token belongs to the signed-in user and compatible clients manage refresh automatically. Never place tokens in a URL, prompt, or shared configuration file; the source accepts tokens in the Authorization header and warns about URL logs, browser history, and Referer headers.

Step 3: Use local stdio for one person

For DataHub Core or a local single-user setup, install uv and set DATAHUB_GMS_URL and DATAHUB_GMS_TOKEN only in a secure local environment. Then run uvx mcp-server-datahub and add that stdio command to the client configuration. The server can also read ~/.datahubenv, created through datahub init. After starting, test with a low-risk search for a known non-sensitive asset and check that the agent receives only expected metadata.

bash
uvx mcp-server-datahub

Operate shared HTTP safely

For a team, use the separate HTTP entry point and configure only DATAHUB_GMS_URL. Never set a global DATAHUB_GMS_TOKEN on a shared server: the official server intentionally refuses that startup so every request uses the person's own bearer token and permissions and audit identity do not collapse into one account. Enable METADATA_SERVICE_AUTH_ENABLED=true in DataHub, enforce TLS at an ingress or reverse proxy, and apply rate limiting. The health endpoint is intentionally unauthenticated but returns only process status.

Step 4: Start read-only; deliberately enable changes

Discovery and inspection tools read catalog state. Keep mutation tools disabled while the use case is search, analysis, or research. Only TOOLS_IS_MUTATION_ENABLED=true enables changes to tags, terms, owners, domains, descriptions, or structured properties. Plan a separate approval, limited account, and proposal or review process for this. An AI agent can misinterpret instructions; independently confirm every business-relevant change outside the chat.

Control the model path and operation

The MCP server returns results to the connected client. Review that client's model provider, telemetry, logging, retention, and data residency. A local server installation does not automatically mean that returned metadata stays local. Use short task-specific queries, limit visibility before search, and keep tokens out of shell history, screenshots, and support tickets. This keeps DataHub MCP a catalog and research tool rather than an unrestricted data path.

uvx mcp-server-datahub

Authentication

DataHub Cloud supports OAuth with a personal login. Self-hosted stdio uses DATAHUB_GMS_URL and DATAHUB_GMS_TOKEN; shared HTTP requires a bearer token per request in the Authorization header.

Required access permissions

Visible catalog context follows the DataHub user or service account and its policies. Default Views can limit a service account search to specific data assets.

Transmitted or stored data

The server returns DataHub metadata and query context to the MCP client. Those results can be processed, logged, or sent to the connected model provider by that client.

Security risks

Catalog metadata, query history, and lineage can disclose sensitive architecture or business details. Broad tokens and enabled mutation tools increase exposure or unintended metadata-change risk; shared HTTP needs TLS, rate limiting, and individual tokens.

License and costs

License
Apache-2.0
Cost
free

The MCP server is Apache-2.0 licensed. Availability and terms for DataHub Cloud, self-hosted infrastructure, and AI clients depend on the respective provider and deployment.

Alternatives

Not recorded yet.

At a glance

Provider
Acryl Data
Status
Official server
Deployment
Local and remote
Current version
Not recorded yet.
GitHub stars
85
Last reviewed
08.09.2026

Repository and documentation

Categories

Supported clients

Related guides

Guides and background related to this entry.

No related guides yet.