Databricks
Enables LLM-powered tools to interact with Databricks clusters, jobs, notebooks, SQL warehouses, and Unity Catalog through the Model Completion Protocol. Provides comprehensive access to Databricks REST API functionality including cluster management,
What is Databricks?
Databricks is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to enables llm-powered tools to interact with databricks clusters, jobs, notebooks, sql warehouses, and unity catalog through the model completion protocol. provides comprehensive access to databricks re...
Enables LLM-powered tools to interact with Databricks clusters, jobs, notebooks, SQL warehouses, and Unity Catalog through the Model Completion Protocol. Provides comprehensive access to Databricks REST API functionality including cluster management,
This server falls under the Data Science & ML and Cloud Services categories on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Enables LLM-powered tools to interact with Databricks cluste
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx databricks-mcp-serverConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Databricks
The Databricks MCP Server exposes Databricks workspace capabilities — SQL queries, job management, and cluster inspection — to AI assistants through the Model Context Protocol. It connects to your Databricks SQL warehouse using a personal access token, enabling natural language interactions with your big data analytics platform without leaving your AI chat interface. This is particularly useful for data engineers and analysts who want to run ad-hoc queries, monitor jobs, or explore data without context-switching to the Databricks UI.
Prerequisites
- Python 3.7+ installed on your local machine
- A Databricks workspace with a SQL warehouse provisioned
- A Databricks personal access token with permissions to run SQL queries and list jobs
- The HTTP path of your SQL warehouse (found in the Databricks SQL warehouse connection details)
- An MCP client such as Claude Desktop
Clone the repository
Download the server source code from GitHub to your local machine.
git clone https://github.com/JordiNeil/mcp-databricks-server.git
cd mcp-databricks-serverCreate a virtual environment and install dependencies
Isolate the server's Python dependencies in a virtual environment to avoid conflicts.
python -m venv .venv
source .venv/bin/activate
pip install -r requirements.txtGather your Databricks credentials
You need three values: your workspace URL (e.g. https://adb-xxxx.azuredatabricks.net), a personal access token (Settings > Developer > Access tokens), and the HTTP Path from your SQL warehouse's Connection Details tab.
Test the connection
Run the included test script to verify your credentials and warehouse connectivity before wiring up the MCP server.
DATABRICKS_HOST=https://adb-xxxx.azuredatabricks.net \
DATABRICKS_TOKEN=dapiXXXXXXXXXXXX \
DATABRICKS_HTTP_PATH=/sql/1.0/warehouses/xxxx \
python test_connection.pyConfigure Claude Desktop
Add the server entry to your Claude Desktop config, providing the three required environment variables so the server can authenticate to Databricks.
{
"mcpServers": {
"databricks": {
"command": "/path/to/mcp-databricks-server/.venv/bin/python",
"args": ["/path/to/mcp-databricks-server/main.py"],
"env": {
"DATABRICKS_HOST": "https://adb-xxxx.azuredatabricks.net",
"DATABRICKS_TOKEN": "dapiXXXXXXXXXXXX",
"DATABRICKS_HTTP_PATH": "/sql/1.0/warehouses/xxxx"
}
}
}
}Restart Claude Desktop and verify
Quit and relaunch Claude Desktop. The Databricks tools should appear in the MCP tool panel. Try asking a simple question to confirm connectivity.
Databricks Examples
Client configuration
Claude Desktop configuration using a local Python virtualenv to run the Databricks MCP server.
{
"mcpServers": {
"databricks": {
"command": "/Users/you/mcp-databricks-server/.venv/bin/python",
"args": ["/Users/you/mcp-databricks-server/main.py"],
"env": {
"DATABRICKS_HOST": "https://adb-1234567890.azuredatabricks.net",
"DATABRICKS_TOKEN": "dapiABCDEF1234567890",
"DATABRICKS_HTTP_PATH": "/sql/1.0/warehouses/abc123def456"
}
}
}
}Prompts to try
Sample prompts that use the four 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 records in the customers table"
- "List all Databricks jobs in my workspace"
- "What is the status of job number 123?"
- "Give me the full details for job 456"Troubleshooting Databricks
Connection test fails with 'Invalid access token'
Regenerate your Databricks personal access token under Settings > Developer > Access tokens. Ensure the token has not expired and that you are copying the full token string including the 'dapi' prefix.
SQL queries time out or return no results
Verify DATABRICKS_HTTP_PATH is the HTTP Path from the SQL warehouse Connection Details, not the cluster ID. Also ensure the SQL warehouse is running (not terminated) in the Databricks UI before issuing queries.
Module not found errors when starting the server
Ensure you activated the virtual environment before running pip install, and that Claude Desktop is pointed at the Python binary inside .venv (not the system Python). Use the absolute path to .venv/bin/python in your config.
Frequently Asked Questions about Databricks
What is Databricks?
Databricks is a Model Context Protocol (MCP) server that enables llm-powered tools to interact with databricks clusters, jobs, notebooks, sql warehouses, and unity catalog through the model completion protocol. provides comprehensive access to databricks rest api functionality including cluster management, 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 license. You can use it freely in both personal and commercial projects.
Databricks Alternatives — Similar Data Science & ML Servers
Looking for alternatives to Databricks? Here are other popular data science & ml servers you can use with Claude, Cursor, and VS Code.
Ultrarag
★ 5.6kA Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines
RocketRide
★ 3.1k📇 🏠 - MCP server that exposes RocketRide AI pipelines as t
Aix Db
★ 2.1kAix-DB 基于 LangChain/LangGraph 框架，结合 MCP Skills 多智能体协作架构，实现自然语言到数据洞察的端到端转换。
NeMo Data Designer
★ 1.9k🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.
PaperBanana
★ 1.7kOpen source implementation and extension of Google Research’s PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation.
MiniMax
★ 1.5kBridges MiniMax AI capabilities to the Model Context Protocol, enabling AI agents to perform image understanding, text-to-image generation, and speech synthesis. It provides a standardized interface for accessing MiniMax's core tools via JSON-RPC.
Browse More Data Science & ML MCP Servers
Explore all data science & ml 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.