databricks-mcp
Provides tools to manage and query Databricks workspaces, including clusters, jobs, SQL warehouses, notebooks, MLflow, Unity Catalog, Delta Live Tables, and more.
Supports dbt tasks in job creation and execution.
Enables management of Delta Live Tables (pipelines) and Delta Sharing shares, recipients, and providers.
Supports git-based repositories (Repos) with operations to list, get, create, update, delete, pull, push, and commit.
Provides tools for managing MLflow experiments, runs, models, registered models, model versions, and webhooks.
Allows management of Unity Catalog resources including catalogs, schemas, tables, columns, volumes, functions, and grants.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@databricks-mcplist my active clusters"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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 |
Related MCP server: Databricks MCP Server
Install
# From source (this repo)
uv tool install .
# Or pipx / pip
pipx install .
# or
pip install .
# Or run directly with uvx
uvx --from . databricks-mcpConfigure
The server needs three environment variables (or CLI flags):
Variable | Required | Example |
| yes |
|
| one of PAT or OAuth must be set |
|
| OAuth M2M alternative to PAT | — |
| only for account-level APIs |
|
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-mcpRun 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 8000Test with MCP Inspector
npx -y @modelcontextprotocol/inspector databricks-mcpThen 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.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/inav/databricks-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server