acryldata/mcp-server-datahub

A Model Context Protocol server implementation for DataHub.
What is DataHub?
DataHub is an open-source context platform that gives organizations a single pane of glass across their entire data supply chain. DataHub unifies data discovery, governance, and observability under one roof for every table, column, dashboard pipeline, document, and ML Model.
With powerful features for data profiling, data quality monitoring, data lineage, data ownership, and data classification, DataHub brings together both technical and organizational context, allowing teams to find, create, use, and maintain trustworthy data.
Use Cases
The DataHub MCP Server enables AI agents to:
- **Find trustworthy data**: Search across the entire data landscape using natural language to find the tables, columns, dashboards, & metrics that can answer your most mission-critical questions. Leverage trust signals like data popularity, quality, lineage, and query history to get it right, every time.
- **Explore data lineage & plan for data changes**: Understand the impact of important data changes _before_ they impact your downstream users through rich data lineage at the asset & column level.
- **Understand your business**: Navigate important organizational context like business glossaries, data domains, data products products, _and_ data assets. Understand how key metrics, business processes, and data relate to one another.
- **Explain & generate SQL queries**: Generate accurate SQL queries to answer your most important questions with the help of critical context like data documentation, data lineage, and popular queries across the organization.
Why DataHub MCP Server?
With DataHub MCP Server, you can instantly give AI agents visibility into of your entire data ecosystem. Find and understand data stored in your databases, data lake, data warehouse, and BI visualization tools. Explore data lineage, understand usage & use cases, identify the data experts, and generate SQL - all through natural language.
**Structured Search with Context Filtering**
Go beyond keyword matching with powerful query & filtering syntax:
- Wildcard matching: /q revenue_* finds revenue_kpis, revenue_daily, revenue_forecast
- Field searches: /q tag:PII finds all PII-tagged data
- Boolean logic: /q (sales OR revenue) AND quarterly for complex queries
**SQL Intelligence & Query Generation**
Access popular SQL queries, and generate new ones with accuracy:
- See how analysts query tables (perfect for SQL generation)
- Understand join patterns and common filters
- Learn from production query patterns
**Table & Column-Level Lineage**
Trace data flow at both the table and column level:
- Track how user_id becomes customer_key downstream
- Understand transformation logic
- Upstream and downstream exploration (1-3+ hops)
- Handle enterprise-scale lineage graphs
**Understands Your Data Ecosystem**
Understand how your data is organized before searching:
- Discover relevant data domains, owners, tags and glossary terms
- Browse across data platforms and environments
- Navigate the complexities of your data landscape without guessing
Usage
See instructions in the DataHub MCP server docs.
Local stdio deployment
The default transport remains stdio for local MCP clients:
The stdio server loads DATAHUB_GMS_URL and DATAHUB_GMS_TOKEN from the
environment, falling back to ~/.datahubenv created by datahub init. This is
the local deployment mode and does not require HTTP authentication.
The local CLI also supports SSE for trusted, local-network use. SSE does not
provide the per-request bearer authentication used by the dedicated HTTP
entry point and should not be exposed as a shared network service.
Docker HTTP deployment
The container runs the stateless HTTP transport on port 8000. It deliberately
does not use a server-wide DATAHUB_GMS_TOKEN; each MCP client supplies its own
DataHub token so DataHub permissions and audit identity are preserved per user.