Skip to main content

DataHub Extension

🎥Plug & Play
Watch the demo

This tutorial covers how to add the DataHub MCP Server as a goose extension to enable AI-powered data discovery, lineage exploration, and metadata querying across your data ecosystem.

TLDR

Launch the installer

Environment Variables

DATAHUB_GMS_URL: <your-datahub-url>
DATAHUB_GMS_TOKEN: <your-datahub-token>

What is DataHub?​

DataHub is an open-source metadata platform that provides a unified view of your data ecosystem, cataloging datasets, dashboards, pipelines, and more with rich metadata including ownership, lineage, usage statistics, and data quality information.

The DataHub MCP Server enables AI agents to:

  • Find trustworthy data using natural language search with trust signals like popularity, quality, and lineage
  • Explore data lineage to understand upstream and downstream dependencies at table and column level
  • Understand business context through glossaries, domains, data products, and organizational metadata
  • Generate SQL queries with help from documentation, lineage, and popular query patterns

Learn more: DataHub MCP Server Guide | GitHub Repository

Prerequisites​

Before using the DataHub MCP Server, ensure you have:

Configuration​

info

Note that you'll need uv installed on your system to run this command, as it uses uvx.

  1. Launch the installer
  2. Click Yes to confirm the installation
  3. Get your DataHub Personal Access Token and paste it in
  4. Click Add Extension
  5. Click the button in the top-left to open the sidebar
  6. Navigate to the chat

Example Usage​

Finding Trustworthy Data​

Find datasets related to your project by describing what you need in natural language.

goose Prompt​

Find all datasets related to customer transactions that are owned by the analytics team

goose Output​

Desktop

The DataHub extension will search across your data catalog and return relevant datasets with their metadata, including:

  • Dataset names and descriptions
  • Column names, types, descriptions, and labels
  • Owners
  • Tags, properties, and glossary terms
  • Usage statistics
  • Data quality status

Exploring Data Lineage​

I want to remove the "timestamp_seconds" column from the customer_orders table. What will break?

goose Prompt​

Show me the upstream lineage for the customer_orders table

goose Output​

Desktop

The extension will traverse the lineage graph and show any:

  • Source tables and datasets
  • Transformation pipelines
  • ETL jobs and workflows
  • Downstream columns

That would be impacted by removing the column.

Generating SQL Queries​

How do I calculate the number of orders made in the USA last year?

goose Prompt​

What are the most common queries run against the customer_orders dataset?

goose Output​

Desktop

The extension will retrieve SQL query history showing:

  • Frequently executed queries
  • Common join patterns
  • Filter conditions
  • Aggregation patterns

In addition to column names, types, descriptions, and any labels. This will enable the agent to generate high quality SQL to answer the question.

Understanding Data Quality & Freshness​

Determine whether a dataset is trustworthy before using it.

goose Prompt​

Is the customer_orders table fresh and free of data quality issues?

goose Output​

Desktop

The extension will fetch:

  • Latest data quality assertions and test results
  • Freshness / staleness metrics
  • Schema change history
  • SLA or SLO metadata
  • Owner-provided health status

Allowing the agent to warn the user or confirm data trustworthiness.

Capabilities​

The DataHub MCP Server provides the following tools:

search

Search DataHub using structured keyword search (/q syntax) with boolean logic, filters, pagination, and optional sorting by usage metrics.

get_lineage

Retrieve upstream or downstream lineage for any entity (datasets, columns, dashboards, etc.) with filtering, query-within-lineage, pagination, and hop control.

get_dataset_queries

Fetch real SQL queries referencing a dataset or column—manual or system-generated—to understand usage patterns, joins, filters, and aggregation behavior.

get_entities

Fetch detailed metadata for one or more entities by URN; supports batch retrieval for efficient inspection of search results.

list_schema_fields

List schema fields for a dataset with keyword filtering and pagination, useful when search results truncate fields or when exploring large schemas.

get_lineage_paths_between

Retrieve the exact lineage paths between two assets or columns, including intermediate transformations and SQL query information.

Resources​

Troubleshooting​

Connection Issues​

If you're having trouble connecting to DataHub:

  1. Verify your DATAHUB_GMS_URL is correct:

    • For DataHub Cloud: https://your-tenant.acryl.io
    • For local instances: http://localhost:8080
    • For on-premises: https://datahub.your-company.com

  2. Confirm your Personal Access Token is valid and has appropriate permissions

  3. Check network connectivity and firewall rules

Installation Issues​

If uvx is not found:

  1. Ensure uv is installed: curl -LsSf https://astral.sh/uv/install.sh | sh
  2. Restart your terminal or source your shell configuration
  3. Verify installation: which uvx