Getting Started with Goose Desktop

Learn how to connect Goose Desktop with MCP Server, create tokens, and enable secure AI-powered access to your data platform.

Getting Started with Goose Desktop

Configure OpenMetadata’s MCP Server to interact with block’s AI agent Goose.

Prerequisites

For this guide, you will need:

• nvm and npx/node version 22
• OpenMetadata v1.8.0 or later- You can upgrade your version of OpenMetadata with this guide
• Goose Desktop
• OpenMetadata MCP Application and Personal Access Token

Adding your OpenMetadata MCP Server to Goose Desktop

This how-to guide uses Goose Desktop for macOS. Make sure that you already have an LLM Provider configured before prompting.

• Navigate to Goose Desktop’s Settings, then under Extensions, select +Add custom extension.

• The custom extension should have the following information:
  • Extension Name OpenMetadata
  • Command paste the following command:
    npx -y mcp-remote <YOUR_OpenMetadata_SERVER>/mcp --auth-server-url=<YOUR_OpenMetadata_SERVER>/mcp --client-id=OpenMetadata --verbose --clean --header Authorization:${AUTH_HEADER}
    
    • If you are running it locally, your command will look like this:
      npx -y mcp-remote http://localhost:8585/mcp --auth-server-url=http://localhost:8585/mcp --client-id=OpenMetadata --verbose --clean --header Authorization:${AUTH_HEADER}
      
  • Add 1 Environment Variable
    • Variable name is AUTH_HEADER
    • Value is Bearer <YOUR_OpenMetadata_PAT>

• Select Add Extension

Prompt to read from OpenMetadata

This part of the guide assumes that you have assets in OpenMetadata. You can add data assets into OpenMetadata here.

Select a model from Goose and paste the following prompt to have it read from OpenMetadata:

What tables do you have access to in OpenMetadata?

For more sample use cases with MCP please check out our blog!

Reach out on Slack!

With MCP, we are finding new ways to use OpenMetadata all the time! Now that you have Claude and OpenMetadata configured to work together, think you’ve got a great new use case? Show us what you’ve got in Slack!