Databricks Permissions MCP Server

Name: Databricks Permissions MCP Server
Author: JustTryAI

@JustTryAI

Repository

About Databricks Permissions MCP Server

MCP server for managing Databricks permissions and credentials

Basic information

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "databricks-permissions-mcp-server": {
      "command": "python",
      "args": [
        "-m",
        "venv",
        ".venv"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Databricks Permissions MCP Server?

A Model Completion Protocol (MCP) server that provides access to Databricks permissions, credentials, and Git credentials via the MCP protocol. It allows LLM-powered tools like Claude to interact with Databricks permissions management systems.

How to use Databricks Permissions MCP Server?

Clone the repository, set up a Python virtual environment with Python 3.10+, install dependencies with pip install -e ., and configure the environment variables DATABRICKS_HOST and DATABRICKS_TOKEN. Run the server using ./start_mcp_server.sh (Linux/Mac) or .\start_mcp_server.ps1 (Windows), or add a custom command in Claude Desktop pointing to python -m src.server.databricks_permissions_mcp_server.

Key features of Databricks Permissions MCP Server

MCP protocol support for LLM integration
Databricks API secure access for permissions
Comprehensive permission management tools
Git credentials management (CRUD)
Async support for efficient operation

Use cases of Databricks Permissions MCP Server

List all Git credentials in Databricks via natural language
Show permissions for a specific cluster
Update permissions for a job to grant user access
Manage Unity Catalog permissions (catalogs, schemas, tables)
Create, update, and delete service principals

FAQ from Databricks Permissions MCP Server

What are the prerequisites for running the server?

Python 3.10 or higher and an MCP-compatible client (e.g., Claude Desktop).

How do I authenticate with Databricks?

Set the DATABRICKS_HOST and DATABRICKS_TOKEN environment variables with your Databricks workspace URL and personal access token.

What Databricks resources are supported for permissions?

Clusters, jobs, SQL warehouses, workspace objects (notebooks, directories), Unity Catalog (catalogs, schemas, tables), and service principals. Git credentials are also managed separately.