Databricks Sql MCP
A server based on the Model Context Protocol that allows AI assistants such as Claude to connect to the Databricks SQL data warehouse through a Docker container, execute SQL queries, browse databases and table structures, and support hierarchical data management in the Unity Catalog.
rating : 2 points
downloads : 4.2K
What is the Databricks SQL MCP Server?
This is a bridge that connects AI assistants (such as Claude) with the Databricks data platform. It allows you to query and analyze data stored in Databricks through natural language conversations, as simple as talking to a data expert. You can directly ask Claude: 'Show the top 10 products with the highest sales' or 'What fields are there in the customer data?', and the system will automatically convert your request into an SQL query and return the results.How to use the Databricks SQL MCP Server?
The usage process is very simple: 1) Install Docker and Claude Desktop; 2) Run the one-click installation script; 3) Provide your Databricks access credentials; 4) Restart Claude and start conversational queries. The whole process only takes a few minutes and no programming knowledge is required.Applicable scenarios
Suitable for users such as data analysts, business personnel, and product managers who need to quickly obtain data insights but do not want to write complex SQL. Common scenarios include: exploratory data analysis, daily business reports, data quality checks, ad-hoc data queries, etc.Main features
SQL query execution
Directly run any SQL query statement, supporting all standard SQL operations such as SELECT, JOIN, GROUP BY, etc. Query results are returned in a clear tabular form.
Data catalog browsing
Browse the three-tier structure in the Databricks Unity Catalog: Catalog → Schema → Table, helping you understand the data organizational structure.
Table structure viewing
View the detailed structure of any data table, including column names, data types, comments, and other information, helping you understand the meaning of the data.
Multi-platform support
Supports Databricks workspaces on the three major cloud platforms of Azure, AWS, and GCP, adapting to different enterprise deployment environments.
One-click installation
Provides an automated installation script. You can complete all configurations by running a single command, greatly simplifying the installation process.
Advantages
No SQL expertise required: Query data through natural language, reducing the technical threshold
Fast installation and configuration: The one-click installation script simplifies the deployment process
Secure and reliable: Uses personal access tokens and does not store sensitive credentials
Real-time interaction: Query results are returned immediately, supporting iterative data analysis
Cross-platform compatibility: Supports both Claude Desktop and Claude Code usage modes
Limitations
Requires a Docker environment: Must run on a system with Docker installed
Depends on network connection: Needs to be able to access the Databricks workspace
SQL warehouse must be running: Ensure that the SQL warehouse is running before querying
Permission restrictions: Can only access data with existing user permissions
Requires a Claude subscription: Must use the Claude AI assistant
How to use
Prepare the environment
Ensure that Docker is installed and running on your computer, and also install Claude Desktop or Claude Code.
Obtain Databricks credentials
Log in to your Databricks workspace and obtain the following three necessary pieces of information: workspace URL, personal access token, and SQL warehouse ID.
Run the installation script
Run the corresponding installation script according to your operating system. The script will automatically download the Docker image and configure Claude.
Restart Claude and start using
Restart Claude Desktop or start a new Claude Code session. You can now query Databricks data through conversations.
Usage examples
Explore the data catalog structure
When you first encounter a Databricks environment, you first need to understand the data organizational structure. Through natural language conversations, you can quickly browse the entire data catalog.
Quick data sampling check
When analyzing a new data table, you need to first view the data sample and structure to understand the field meanings and data quality.
Business metric calculation
Business personnel need to calculate key metrics, such as monthly sales, user growth rate, etc., without writing complex SQL.
Data quality verification
After the data pipeline runs, you need to verify whether the data is complete and accurate, and check for issues such as null values and duplicate values.
Frequently Asked Questions
Do I need to pay to use this tool?
Is my data secure? Where will the credentials be stored?
Why does the query fail and show 'SQL Warehouse not running'?
What SQL syntax is supported? Can UPDATE or DELETE be executed?
What should I do if Claude cannot find the server after installation?
Can I connect to multiple Databricks workspaces?
Related resources
GitHub code repository
View the complete source code, report issues, and submit feature requests
Docker image page
Download the pre - built Docker image and view the image version
Model Context Protocol official website
Understand the MCP protocol standard and explore other MCP servers
Databricks official documentation
Learn to use the Databricks platform and configure the SQL warehouse
Claude Desktop download
Download the Claude Desktop application

Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
24.6K
4.3 points

Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
35.5K
5 points

Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
21.4K
4.5 points

Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
73.1K
4.3 points

Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
65.6K
4.5 points

Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
32.3K
5 points

Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
22.1K
4.5 points

Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
49.1K
4.8 points





