- Home
- MCP servers
- Databricks Permissions
Databricks Permissions
- typescript
0
GitHub Stars
typescript
Language
7 months ago
First Indexed
3 months ago
Catalog Refreshed
Documentation & install
Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.
Installation
Add the following to your MCP client configuration file.
Configuration
View docs{
"mcpServers": {
"justtryai-databricks-permissions-mcp-server": {
"command": "python",
"args": [
"-m",
"src.server.databricks_permissions_mcp_server"
],
"env": {
"DATABRICKS_HOST": "https://your-databricks-instance.azuredatabricks.net",
"DATABRICKS_TOKEN": "your-personal-access-token"
}
}
}
}This MCP server provides controlled access to Databricks permissions, credentials, and Git credentials through the MCP protocol. It enables AI-powered tools to manage Databricks resources securely and efficiently by exposing a curated set of permission and credential management operations.
How to use
You use this MCP server with an MCP client to perform permission and credential tasks against Databricks. You can fetch current permissions, set or update permissions for clusters, jobs, warehouses, and workspace objects, manage Unity Catalog permissions, handle service principals, and administer Git credentials. You will issue commands through your MCP client to invoke the available tools, and the server will translate those requests into Databricks API calls.
How to install
Prerequisites you need before installation are Python 3.10 or higher and an MCP-compatible client (for example, Claude Desktop). Ensure you have network access to your Databricks instance and your workspace permissions allow you to manage the resources you intend to modify.
Step by step installation flow you can follow locally:
# 1) Clone the project
git clone https://github.com/yourusername/databricks-permissions-mcp-server.git
cd databricks-permissions-mcp-server
# 2) Set up a Python virtual environment
python -m venv .venv
# 3) Activate the virtual environment
# Windows
.\.venv\Scripts\activate
# Linux/Mac
source .venv/bin/activate
# 4) Install dependencies in development mode
pip install -e .
Running the MCP server
To start the MCP server locally, run the appropriate startup script for your platform.
Windows users can start the server with the provided PowerShell script.
Linux or macOS users can start the server with the provided shell script.
Available tools
get_permissions
Retrieve the permissions for a specified Databricks object.
set_permissions
Apply or replace permissions on a Databricks object.
update_permissions
Modify existing permissions for a Databricks object.
get_permission_levels
List available permission levels for a given Databricks object type.
get_cluster_permissions
Fetch permissions for a specific cluster.
set_cluster_permissions
Set permissions for a specific cluster.
update_cluster_permissions
Update permissions for a specific cluster.
get_job_permissions
Fetch permissions for a specific job.
set_job_permissions
Set permissions for a specific job.
get_warehouse_permissions
Fetch permissions for a SQL warehouse.
get_workspace_object_permissions
Get permissions for a workspace object like notebooks or directories.
list_service_principals
List all service principals in the workspace.
get_service_principal
Get details for a specific service principal.
create_service_principal
Create a new service principal.
update_service_principal
Update an existing service principal.
delete_service_principal
Delete a service principal.
get_catalog_permissions
Get permissions for a Unity Catalog catalog.
get_schema_permissions
Get permissions for a Unity Catalog schema.
get_table_permissions
Get permissions for a Unity Catalog table.
list_git_credentials
List all Git credentials.
create_git_credential
Create a new Git credential.
update_git_credential
Update an existing Git credential.
delete_git_credential
Delete a Git credential.