MCP Databricks Server

An MCP server that connects to the Databricks API, supporting functions such as executing SQL queries and managing jobs.

Cloud platform Developer tools #Data query #Job management #Databricks #API connection .Python

rating : 2.5 points

downloads : 34

update time : 2025-04-28

What is the Databricks MCP Server?

This is an intelligent interface service that converts natural language instructions into actual operations on the Databricks platform. By connecting to a large language model (LLM), you can query data and manage tasks in everyday language without writing complex code.

How to use the Databricks MCP Server?

Simply start the service and connect an AI assistant that supports the MCP protocol to interact with Databricks through conversations. The system will automatically handle complex processes such as authentication, SQL conversion, and task scheduling.

Use cases

Suitable for business personnel who need to query data frequently but are not proficient in SQL, or teams that want to manage data workflows in natural language, which can significantly improve data analysis efficiency.

Main features

Intelligent SQL queryConvert natural language into optimized SQL statements, execute them in the Databricks data warehouse, and return structured results

Workflow managementView the list of all data processing tasks and get real-time status and detailed configuration information

Status monitoringQuery the running status and historical records of specific tasks at any time

Advantages and limitations

Advantages

No need to memorize complex commands, operate the data platform in natural language

Lower the technical threshold, business personnel can obtain data independently

Unify the management of queries and tasks to improve work efficiency

Limitations

Need to pre - configure Databricks access permissions

Complex queries may require manual optimization

Depend on network connection and API stability

How to use

Environment preparation

Ensure that Python 3.7+ is installed and you have a valid Databricks account

Get credentials

Get the access token and warehouse information from the Databricks console

Configure the service

Set the host address, token, and SQL warehouse path in the.env file

Start the service

Run the main program to start the MCP protocol service

Usage examples

Sales data analysisThe marketing team needs to understand the quarterly sales trends

Task status checkData engineers monitor nightly batch processing tasks

Frequently Asked Questions

How to get a Databricks access token?

Is there a size limit for SQL queries?

What if the service fails to start?

Related resources

Databricks official documentation

A complete guide to using the Databricks platform

MCP protocol specification

Technical standards for the Model Context Protocol

Example code library

More configuration examples and usage scenarios

🚀 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

Clone this repository.

Create and activate a virtual environment (recommended):

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

Install the dependencies:
```
pip install -r requirements.txt
```

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

Test your connection (optional but recommended):
```
python test_connection.py
```

Obtaining Databricks Credentials

Host: Your Databricks instance URL (e.g., your-instance.cloud.databricks.com).
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.
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:

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