Databricks
MCP Server for Databricks
What is Databricks?
Databricks is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp server for databricks
MCP Server for Databricks
This server falls under the Databases category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- MCP Server for Databricks
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx mcp-databricksConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Databricks
The Databricks MCP Server connects AI assistants to a Databricks workspace, exposing four tools that let your LLM run SQL queries against a SQL warehouse, list all workspace jobs, check job status by ID, and retrieve detailed job configuration and history. This enables natural-language data analysis workflows where you ask questions about your data and the AI translates them to SQL and executes them directly — without leaving your MCP client. It also makes job orchestration visible to AI agents, useful for monitoring pipeline status or triggering ad-hoc analysis.
Prerequisites
- Python 3.7 or later with pip
- A running Databricks workspace with a SQL warehouse (cluster must be started)
- A Databricks personal access token from User Settings → Developer tab in the workspace UI
- The HTTP path of your SQL warehouse (found in the warehouse connection details)
- An MCP client such as Claude Desktop or Claude Code
Clone the repository
Clone the mcp-databricks-server repository from GitHub.
git clone https://github.com/JordiNeil/mcp-databricks-server.git
cd mcp-databricks-serverCreate a virtual environment and install dependencies
Set up a Python virtual environment and install the required packages.
python -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install -r requirements.txtCreate and populate the .env file
Create a .env file in the project root with your Databricks credentials. Never commit this file to version control.
# .env
DATABRICKS_HOST=your-workspace.cloud.databricks.com
DATABRICKS_TOKEN=dapi1234567890abcdef
DATABRICKS_HTTP_PATH=/sql/1.0/warehouses/your-warehouse-idTest the database connection
Run the included test script to verify credentials and warehouse connectivity before configuring MCP.
python test_connection.pyStart the MCP server
Launch the server. It communicates over stdio, so your MCP client will start it automatically once configured.
python main.pyConfigure your MCP client
Add the server to your MCP client configuration. The command launches the Python server and passes environment variables from the .env file.
{
"mcpServers": {
"databricks": {
"command": "python",
"args": ["/absolute/path/to/mcp-databricks-server/main.py"],
"env": {
"DATABRICKS_HOST": "your-workspace.cloud.databricks.com",
"DATABRICKS_TOKEN": "<your-personal-access-token>",
"DATABRICKS_HTTP_PATH": "/sql/1.0/warehouses/your-warehouse-id"
}
}
}
}Databricks Examples
Client configuration
Complete Claude Desktop configuration for the Databricks MCP server with credentials passed as environment variables.
{
"mcpServers": {
"databricks": {
"command": "python",
"args": ["/path/to/mcp-databricks-server/main.py"],
"env": {
"DATABRICKS_HOST": "your-workspace.cloud.databricks.com",
"DATABRICKS_TOKEN": "<your-personal-access-token>",
"DATABRICKS_HTTP_PATH": "/sql/1.0/warehouses/your-warehouse-id"
}
}
}
}Prompts to try
These prompts exercise the four Databricks tools: run_sql_query, list_jobs, get_job_status, and get_job_details.
- "Show me all tables in the default database."
- "Run a SQL query to count the number of rows in the sales.orders table."
- "List all Databricks jobs in my workspace."
- "Check the status of Databricks job number 123."
- "Get the full configuration and recent run history for job 456."
- "How many orders were placed last month? Query the orders table to find out."Troubleshooting Databricks
Connection error: 'Unauthorized' or 403 when running SQL queries.
Verify DATABRICKS_TOKEN is a valid personal access token and has not expired. Generate a new token in your Databricks workspace under User Settings → Developer → Access Tokens. Also confirm the token has permission to access the specified SQL warehouse.
SQL queries hang or time out without returning results.
Check that your SQL warehouse is in the Running state in the Databricks UI — warehouses auto-terminate after inactivity and may take 2–5 minutes to start. Also confirm DATABRICKS_HTTP_PATH matches the exact HTTP Path shown in the warehouse connection details page.
ModuleNotFoundError on startup.
Ensure you activated the virtual environment before running the server ('source .venv/bin/activate' on macOS/Linux or '.venv\Scripts\activate' on Windows). If a specific module is missing, re-run 'pip install -r requirements.txt' inside the active venv.
Frequently Asked Questions about Databricks
What is Databricks?
Databricks is a Model Context Protocol (MCP) server that mcp server for databricks It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Databricks?
Follow the installation instructions on the Databricks GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Databricks?
Databricks works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Databricks free to use?
Yes, Databricks is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Databricks Alternatives — Similar Databases Servers
Looking for alternatives to Databricks? Here are other popular databases servers you can use with Claude, Cursor, and VS Code.
Excelize
★ 20.6kGo language library for reading and writing Microsoft Excel™ (XLAM / XLSM / XLSX / XLTM / XLTX) spreadsheets
MCP Toolbox for Databases
★ 15.3kOpen source MCP server specializing in easy, fast, and secure tools for Databases.
DBHub
★ 2.8kA universal database gateway MCP server that enables AI assistants to connect to and query multiple databases (PostgreSQL, MySQL, MariaDB, SQL Server, SQLite) with support for schema exploration, SQL execution, and secure connections via SSH tunnels.
Tabularis
★ 2.1kA lightweight, cross-platform database client for developers. Supports MySQL, PostgreSQL and SQLite. Hackable with plugins. Built for speed, security, and aesthetics.
Postgres AI Guide
★ 1.7kMCP server and Claude plugin for Postgres skills and documentation. Helps AI coding tools generate better PostgreSQL code.
Anyquery
★ 1.7k🏎️ 🏠 ☁️ - Query more than 40 apps with one binary using SQL. It can also connect to your PostgreSQL, MySQL, or SQLite compatible database. Local-first and private by design.
Browse More Databases MCP Servers
Explore all databases servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Databricks in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Databricks?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.