DataHub MCP Server Integration

What does “DataHub” MCP Server do?

The DataHub MCP (Model Context Protocol) Server acts as a bridge between AI assistants and your DataHub data ecosystem. By exposing DataHub’s powerful metadata and context APIs via the MCP standard, this server enables AI agents to search across all entity types, fetch detailed metadata, traverse data lineage, and list associated SQL queries. This dramatically improves development workflows by allowing AI models to access up-to-date data context, perform complex queries, and automate metadata exploration directly from your preferred AI interface. DataHub MCP Server supports both DataHub Core and DataHub Cloud, making it a versatile solution for organizations seeking to integrate their metadata platform with AI-driven tools and assistants.

List of Prompts

No prompt templates are detailed or mentioned in the repository or README.

Ready to grow your business?

Start your free trial today and see results within days.

Request demo Log in

List of Resources

No explicit MCP resource primitives are described in the repository or README.

List of Tools

• Search across all entity types and using arbitrary filters
  Enables clients to query DataHub entities (datasets, dashboards, pipelines, etc.) using custom filters.
• Fetch metadata for any entity
  Retrieves comprehensive metadata about a specific DataHub entity.
• Traverse the lineage graph (upstream and downstream)
  Allows exploration of data lineage, both upstream (sources) and downstream (consumers) for a given entity.
• List SQL queries associated with a dataset
  Surfaces SQL queries linked to a particular dataset for auditing and understanding data usage.

Join our newsletter

Get latest tips, trends, and deals for free.

Email address

Subscribe

Use Cases of this MCP Server

• Comprehensive Data Discovery
  Developers and data scientists can search and filter across all DataHub entities, accelerating data discovery and reducing manual effort.
• Automated Metadata Fetching
  AI agents can programmatically retrieve detailed entity metadata, supporting automated documentation, quality checks, or onboarding workflows.
• Lineage Analysis for Impact Assessment
  By traversing upstream and downstream lineage, teams can instantly assess the impact of changes and improve data governance.
• SQL Query Auditing
  Easily list and analyze SQL queries associated with datasets, aiding in compliance monitoring, performance tuning, and data access optimization.
• Integration With AI-Powered Agents
  Seamlessly connect DataHub with modern AI assistants to automate repetitive data management and exploration tasks directly from chat or code environments.

How to set it up

Windsurf

No Windsurf-specific instructions found in the repository.

Claude

1. Install uv .

2. Locate the full path to the uvx command using which uvx.

3. Obtain your DataHub URL and personal access token.

4. Edit your claude_desktop_config.json file:

   {
     "mcpServers": {
       "datahub": {
         "command": "<full-path-to-uvx>",  // e.g. /Users/hsheth/.local/bin/uvx
         "args": ["mcp-server-datahub"],
         "env": {
           "DATAHUB_GMS_URL": "<your-datahub-url>",
           "DATAHUB_GMS_TOKEN": "<your-datahub-token>"
         }
       }
     }
   }
   

5. Save and (re)start Claude Desktop. Verify connection in the agent interface.

Cursor

1. Install uv .

2. Obtain your DataHub URL and personal access token.

3. Edit .cursor/mcp.json:

   {
     "mcpServers": {
       "datahub": {
         "command": "uvx",
         "args": ["mcp-server-datahub"],
         "env": {
           "DATAHUB_GMS_URL": "<your-datahub-url>",
           "DATAHUB_GMS_TOKEN": "<your-datahub-token>"
         }
       }
     }
   }
   

4. Save the file and restart Cursor. Check the MCP status panel.

Cline

No Cline-specific instructions found in the repository.

Generic/Other MCP Clients

1. Install uv .

2. Prepare your DataHub URL and personal access token.

3. Use this configuration:

   command: uvx
   args:
     - mcp-server-datahub
   env:
     DATAHUB_GMS_URL: <your-datahub-url>
     DATAHUB_GMS_TOKEN: <your-datahub-token>
   

4. Integrate this command in your MCP client configuration.

Securing API Keys

Always store sensitive credentials like DATAHUB_GMS_TOKEN in environment variables, not in plaintext files. In your configuration, use the env field as shown above to inject secrets securely.

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "datahub": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “datahub” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

I would rate this MCP server at about 6/10. It has a clear open-source license, multiple real tools, and basic secure setup instructions, but lacks documented prompt templates, explicit resource primitives, and advanced MCP features like sampling or roots.

MCP Score