Databricks Unity Catalog
Model Context Protocol (MCP) server for Databricks that empowers AI agents to autonomously interact with Unity Catalog metadata. Enables data discovery, lineage analysis, and intelligent SQL execution. Agents explore catalogs/schemas/tables, understa
What is Databricks Unity Catalog?
Databricks Unity Catalog is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to model context protocol (mcp) server for databricks that empowers ai agents to autonomously interact with unity catalog metadata. enables data discovery, lineage analysis, and intelligent sql execution...
Model Context Protocol (MCP) server for Databricks that empowers AI agents to autonomously interact with Unity Catalog metadata. Enables data discovery, lineage analysis, and intelligent SQL execution. Agents explore catalogs/schemas/tables, understa
This server falls under the Databases category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Model Context Protocol (MCP) server for Databricks that empo
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx mcp-databricks-serverConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Databricks Unity Catalog
The MCP Databricks Server connects AI agents to Databricks Unity Catalog, enabling them to autonomously discover data assets, explore catalog and schema metadata, inspect table lineage, and execute SQL queries against a Databricks SQL warehouse. It exposes five focused tools that allow an agent to traverse the full data catalog hierarchy — from catalog listing down to column-level metadata and upstream/downstream lineage — and then run queries to surface insights, making it ideal for data discovery, impact analysis, and ad-hoc analytics workflows.
Prerequisites
- Python 3.10 or later with pip or uv installed
- A Databricks workspace URL and personal access token with Unity Catalog read permissions
- A running Databricks SQL warehouse with its warehouse ID
- An MCP-compatible client such as Claude Desktop
Clone the repository
Clone the project and navigate into it before installing dependencies.
git clone https://github.com/RafaelCartenet/mcp-databricks-server.git
cd mcp-databricks-serverInstall Python dependencies
Install required packages using pip or uv into your active Python environment.
pip install -r requirements.txt
# or with uv:
uv pip install -r requirements.txtCreate a .env file with your Databricks credentials
Create a .env file in the project root containing your workspace host, personal access token, and SQL warehouse ID.
DATABRICKS_HOST=https://your-workspace.azuredatabricks.net
DATABRICKS_TOKEN=dapi1234567890abcdef
DATABRICKS_SQL_WAREHOUSE_ID=abc123def456Configure Claude Desktop
Add the server to your Claude Desktop configuration, pointing to the Python executable and the server entry point inside the cloned repo.
{
"mcpServers": {
"databricks": {
"command": "python",
"args": ["/absolute/path/to/mcp-databricks-server/main.py"],
"env": {
"DATABRICKS_HOST": "https://your-workspace.azuredatabricks.net",
"DATABRICKS_TOKEN": "dapi1234567890abcdef",
"DATABRICKS_SQL_WAREHOUSE_ID": "abc123def456"
}
}
}
}Restart Claude Desktop and verify
Relaunch Claude Desktop. You should see the Databricks tools loaded. Test by asking Claude to list your Unity Catalogs.
Databricks Unity Catalog Examples
Client configuration
claude_desktop_config.json entry for the Databricks MCP server using environment variables.
{
"mcpServers": {
"databricks": {
"command": "python",
"args": ["/Users/yourname/projects/mcp-databricks-server/main.py"],
"env": {
"DATABRICKS_HOST": "https://adb-1234567890.12.azuredatabricks.net",
"DATABRICKS_TOKEN": "dapi_your_token_here",
"DATABRICKS_SQL_WAREHOUSE_ID": "your_warehouse_id"
}
}
}
}Prompts to try
Example prompts that exercise Unity Catalog discovery and SQL execution.
- "List all Unity Catalogs available in my Databricks workspace"
- "Show me all schemas inside the 'production' catalog"
- "Describe the 'sales.orders' table including its columns and types"
- "What are the upstream data sources and downstream consumers of the 'analytics.revenue' table?"
- "Run a SQL query: SELECT customer_id, SUM(amount) FROM production.sales.orders GROUP BY customer_id LIMIT 20"Troubleshooting Databricks Unity Catalog
403 Forbidden when listing catalogs or executing SQL
The personal access token must have SELECT privilege on Unity Catalog objects and USE CATALOG / USE SCHEMA grants. Confirm permissions in Databricks under Data > Unity Catalog > Permissions, or ask a workspace admin to grant BROWSE privilege on the metastore.
SQL warehouse returns 'Warehouse is stopped'
The SQL warehouse referenced by DATABRICKS_SQL_WAREHOUSE_ID must be running or set to auto-start. Navigate to SQL > SQL Warehouses in the Databricks UI, find the warehouse, and ensure Auto Stop is configured or manually start it.
ModuleNotFoundError when launching the server
Run pip install -r requirements.txt again inside the virtualenv that Claude Desktop's command points to. If using a system Python, prefix the command with the full path to the venv Python binary instead.
Frequently Asked Questions about Databricks Unity Catalog
What is Databricks Unity Catalog?
Databricks Unity Catalog is a Model Context Protocol (MCP) server that model context protocol (mcp) server for databricks that empowers ai agents to autonomously interact with unity catalog metadata. enables data discovery, lineage analysis, and intelligent sql execution. agents explore catalogs/schemas/tables, understa It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Databricks Unity Catalog?
Follow the installation instructions on the Databricks Unity Catalog GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Databricks Unity Catalog?
Databricks Unity Catalog works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Databricks Unity Catalog free to use?
Yes, Databricks Unity Catalog is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
Databricks Unity Catalog Alternatives — Similar Databases Servers
Looking for alternatives to Databricks Unity Catalog? 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 Unity Catalog 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 Unity Catalog?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.