databricks-mcp

A Model Context Protocol (MCP) server that exposes the Databricks REST APIs as MCP tools so an LLM agent can manage and query a Databricks workspace.

The server speaks MCP over stdio (for Claude Desktop / Claude Code / Cursor / IDE hosts) and supports a single --transport streamable-http mode for remote deployments (Databricks Apps, container, etc.).

Features

Domain	Tools
Workspace	list / get / create / delete / export / import notebooks; list / get / mkdir / delete workspace files and dirs
Clusters	list, get, create, start, terminate, restart, resize, edit, delete; cluster events; cluster policies; instance pools; node types; spark versions
Jobs	list, get, create, run-now, run-now-and-wait, list-runs, get-run, cancel-run, delete; full task types (notebook, spark_jar, python_wheel, dbt, sql, pipeline, run_job, condition, for_each)
SQL Warehouses	list, get, create, start, stop, edit, delete
SQL Queries / Dashboards / Alerts / Data	list / get / run SQL statements, dashboards (legacy + Lakeview), alerts
Unity Catalog	catalogs, schemas, tables, columns, volumes, functions, grants
Delta Live Tables (Pipelines)	list, get, create, start, stop, delete; pipeline updates
MLflow	experiments, runs, models, registered models, model versions, webhooks
Model Serving	serving endpoints (create, list, get, update, delete, query)
Vector Search	endpoints (create, list, get, delete), indexes (create, list, get, delete, upsert, query, scan)
Databricks Apps	list, get, create, update, delete
Repos (Git)	list, get, create, update, delete; pull, push, commit
Secrets	list, put, get, delete scopes and secrets
DBFS	list, get, put, delete files
Tokens	list, create, revoke
Permissions	get / set / update / delete ACLs on jobs, clusters, pipelines, etc.
Identity / SCIM	list users, groups, service principals
Delta Sharing	list / create / update / delete shares, recipients, providers
Genie (AI/BI)	list spaces, ask-question
Utilities	workspace status, current user, whoami

Install

# From source (this repo)
uv tool install .

# Or pipx / pip
pipx install .
# or
pip install .

# Or run directly with uvx
uvx --from . databricks-mcp

Configure

The server needs three environment variables (or CLI flags):

Variable	Required	Example
DATABRICKS_HOST	yes	https://dbc-1234567890.cloud.databricks.com
DATABRICKS_TOKEN	one of PAT or OAuth must be set	dapi... (Personal Access Token)
DATABRICKS_CLIENT_ID + DATABRICKS_CLIENT_SECRET	OAuth M2M alternative to PAT	—
DATABRICKS_ACCOUNT_ID	only for account-level APIs	1234567890

You can also pass them as CLI flags: --host, --token.

Use with Claude Desktop

Add this to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "databricks": {
      "command": "databricks-mcp",
      "env": {
        "DATABRICKS_HOST": "https://dbc-1234567890.cloud.databricks.com",
        "DATABRICKS_TOKEN": "dapi..."
      }
    }
  }
}

Use with Claude Code

claude mcp add databricks \
  --transport stdio \
  --env DATABRICKS_HOST=https://dbc-1234567890.cloud.databricks.com \
  --env DATABRICKS_TOKEN=dapi... \
  -- databricks-mcp

Run from source

# stdio (default)
uv run databricks-mcp

# streamable HTTP (for remote deployment / Databricks Apps)
uv run databricks-mcp --transport streamable-http --host 0.0.0.0 --port 8000

Test with MCP Inspector

npx -y @modelcontextprotocol/inspector databricks-mcp

Then set DATABRICKS_HOST and DATABRICKS_TOKEN in the Inspector's env form and click Connect. Browse the tool list and try whoami first.

License

MIT.