MCP Databricks Server

🚀 Databricks MCP Server

A Model Context Protocol (MCP) server that connects to the Databricks API, enabling large language models to run SQL queries, list jobs, and obtain job statuses.

🚀 Quick Start

This Databricks MCP server allows large language models to interact with your Databricks environment, including running SQL queries, listing jobs, and getting job statuses.

✨ Features

• Run SQL queries on a Databricks SQL warehouse.
• List all Databricks jobs.
• Get the status of a specific Databricks job.
• Retrieve detailed information about a specific Databricks job.

📦 Installation

Prerequisites

• Python 3.7+
• A Databricks workspace with the following:
  • A personal access token
  • A SQL warehouse endpoint
  • Permissions to run queries and access jobs

Installation Steps

1. Clone this repository.
2. Create and activate a virtual environment (recommended):

   python -m venv .venv
   source .venv/bin/activate  # On Windows: .venv\Scripts\activate
   

3. Install the dependencies:

   pip install -r requirements.txt
   

4. Create a .env file in the root directory with the following variables:

   DATABRICKS_HOST=your-databricks-instance.cloud.databricks.com
   DATABRICKS_TOKEN=your-personal-access-token
   DATABRICKS_HTTP_PATH=/sql/1.0/warehouses/your-warehouse-id
   

5. Test your connection (optional but recommended):

   python test_connection.py
   

Obtaining Databricks Credentials

1. Host: Your Databricks instance URL (e.g., your-instance.cloud.databricks.com).
2. Token: Create a personal access token in Databricks:
   • Go to user settings (click on your username in the top right corner).
   • Select the "Developer" tab.
   • Click "Manage" under "Access Tokens".
   • Generate a new token and save it immediately.
3. HTTP Path: For your SQL warehouse:
   • Go to the SQL warehouse in Databricks.
   • Select your warehouse.
   • Find the connection details and copy the HTTP path.

💻 Usage Examples

Run the Server

Start the MCP server:

python main.py

You can test this MCP server using the inspector by running:

npx @modelcontextprotocol/inspector python3 main.py

Available MCP Tools

The following MCP tools are available:

1. run_sql_query(sql: str) - Execute an SQL query on your Databricks SQL warehouse.
2. list_jobs() - List all Databricks jobs in the workspace.
3. get_job_status(job_id: int) - Get the status of a specific Databricks job by job ID.
4. get_job_details(job_id: int) - Get detailed information about a specific Databricks job.

Example Usage with LLM

When used in conjunction with an LLM that supports the MCP protocol, this server allows you to interact with your Databricks environment using natural language:

• "Show all tables in the database."
• "Run a query to see the number of records in the customers table."
• "List all my Databricks jobs."
• "Check the status of job #123."
• "Show details of job #456."

📚 Documentation

Troubleshooting

Connection Issues

• Ensure your Databricks host is correct and does not include the https:// prefix.
• Check that your SQL warehouse is running and accessible.
• Verify that your personal access token has the necessary permissions.
• Run the included test script: python test_connection.py

Security Considerations

• Your Databricks personal access token provides direct access to your workspace.
• Ensure your .env file is secure and never committed to version control.
• Consider using a Databricks token with appropriate permission scopes.
• Run this server in a secure environment.