Skip to content

Configuration

AI Dev Kit’s MCP server uses standard Databricks authentication. Choose the method that fits your workflow.

Set environment variables directly. Simplest option for individual use.

{
"mcpServers": {
"ai-dev-kit": {
"command": "uvx",
"args": ["databricks-ai-dev-kit"],
"env": {
"DATABRICKS_HOST": "https://your-workspace.cloud.databricks.com",
"DATABRICKS_TOKEN": "dapi..."
}
}
}
}

Generate a token in your workspace under Settings > Developer > Access tokens.

The MCP server accepts additional environment variables to customize behavior:

VariableDescriptionDefault
DATABRICKS_HOSTWorkspace URLRequired (unless using profile)
DATABRICKS_TOKENPersonal access token
DATABRICKS_CONFIG_PROFILECLI profile name
DATABRICKS_CLIENT_IDOAuth client ID (M2M)
DATABRICKS_CLIENT_SECRETOAuth client secret (M2M)
DATABRICKS_CLUSTER_IDDefault cluster for command executionAuto-selected
DATABRICKS_WAREHOUSE_IDDefault SQL warehouseAuto-selected

When DATABRICKS_CLUSTER_ID or DATABRICKS_WAREHOUSE_ID are not set, the MCP server automatically selects an available compute resource.

To connect to more than one workspace, add multiple MCP server entries with different names:

{
"mcpServers": {
"ai-dev-kit-dev": {
"command": "uvx",
"args": ["databricks-ai-dev-kit"],
"env": {
"DATABRICKS_CONFIG_PROFILE": "dev"
}
},
"ai-dev-kit-prod": {
"command": "uvx",
"args": ["databricks-ai-dev-kit"],
"env": {
"DATABRICKS_CONFIG_PROFILE": "prod"
}
}
}
}
IssueSolution
DATABRICKS_PROFILE not recognizedUse DATABRICKS_CONFIG_PROFILE — the SDK requires the full variable name
Token expiredRe-generate under Settings > Developer > Access tokens
CLI profile not foundRun databricks auth login to create or refresh the profile
Permission denied on catalog/tableVerify Unity Catalog grants for your user or service principal