Databricks Genie MCP Server

What does “Databricks Genie” MCP Server do?

The Databricks Genie MCP Server is a Model Context Protocol (MCP) server designed to bridge AI assistants and the Databricks Genie API. This integration empowers large language models (LLMs) to interact with Databricks environments using natural language. Through the server, LLMs can perform actions such as listing Genie spaces, retrieving workspace metadata, initiating and managing Genie conversations, and running SQL queries—all via standardized MCP tools. By acting as a connector, the Databricks Genie MCP Server enables developers to enhance their workflows with conversational data exploration, direct SQL querying, and seamless interaction with Databricks conversational agents, streamlining data-driven development and analysis.

List of Prompts

No explicit prompt templates are documented in the repository.

List of Resources

No explicit resources are described in the repository.

List of Tools

• get_genie_space_id()
  Lists available Genie space IDs and titles in your Databricks workspace.
• get_space_info(space_id: str)
  Retrieves the title and description metadata of a specified Genie space.
• ask_genie(space_id: str, question: str)
  Starts a new Genie conversation by posing a natural language question and returns the SQL and result tables.
• follow_up(space_id: str, conversation_id: str, question: str)
  Continues an existing Genie conversation with a follow-up question.

Use Cases of this MCP Server

• Conversational Data Exploration
  Developers and analysts can use natural language to interactively query Databricks data via Genie, making data analysis more accessible and intuitive.
• Automated SQL Query Generation
  The server converts natural language questions into SQL statements, executing them on Genie spaces and returning structured results, saving time and reducing errors.
• Workspace Metadata Retrieval
  Easily fetch metadata (titles, descriptions) about Genie spaces to understand and document available data resources.
• Conversation Management
  Maintain context over multi-turn conversations, allowing for complex analytical workflows where questions build on previous answers.
• Integration with AI Assistants
  Seamlessly add Databricks Genie capabilities to AI-powered IDEs or chat interfaces, streamlining data science workflows within familiar tools.

How to set it up

Windsurf

1. Ensure Python 3.7+ is installed on your system.
2. Clone the Databricks Genie MCP repository and install dependencies.
3. Create a .env file with your Databricks credentials (DATABRICKS_HOST and DATABRICKS_TOKEN).
4. In your Windsurf configuration, add the MCP server using the following JSON snippet:

   {
     "mcpServers": {
       "databricks-genie": {
         "command": "python",
         "args": ["main.py"]
       }
     }
   }
   

5. Restart Windsurf and verify the server appears in your available MCP servers.
6. Securing API Keys:
   Use environment variables to keep credentials safe. Example:

   {
     "env": {
       "DATABRICKS_HOST": "your-databricks-instance.cloud.databricks.com",
       "DATABRICKS_TOKEN": "your-personal-access-token"
     },
     "inputs": {}
   }
   

Claude

1. Install Python 3.7+ and dependencies from the repo.
2. Configure .env with your Databricks host and token.
3. From your project directory, run:

   mcp install main.py
   

4. Open Claude Desktop, navigate to Resources → Add Resource, and select your Genie MCP Server.
5. Start chatting with your Databricks data.

Cursor

1. Ensure all prerequisites and dependencies are met and .env is configured.
2. Add the following to your Cursor configuration:

   {
     "mcpServers": {
       "databricks-genie": {
         "command": "python",
         "args": ["main.py"]
       }
     }
   }
   

3. Save configuration and restart Cursor.
4. Verify the server connection and ensure environment variables are set as shown above.

Cline

1. Install Python 3.7+, clone the repo, and set up your .env.
2. Add the MCP server in your Cline config:

   {
     "mcpServers": {
       "databricks-genie": {
         "command": "python",
         "args": ["main.py"]
       }
     }
   }
   

3. Restart Cline and verify the MCP server is active.
4. Use environment variables to protect your credentials.

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:

{
  "databricks-genie": {
    "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 “databricks-genie” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Our opinion

The Databricks Genie MCP Server provides a practical bridge between Databricks and LLMs, with clear setup instructions and tooling. However, it lacks prompt templates, explicit resources, and documentation on advanced MCP features like sampling or roots. The core tools are well-defined and useful for Databricks users. Overall, it scores above average but would benefit from richer MCP feature utilization.

MCP Score