How to Use the Databricks MCP in Google ADK

Feed your Databricks lakehouse metadata directly into Google ADK for long-context Gemini reasoning.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Databricks MCP to Google ADK

Create your Vinkius account to connect Databricks to Google ADK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Databricks with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Databricks MCP Server for Gemini

Google ADK thrives on massive context windows. Hook up this MCP Server, and your Gemini models ingest your entire Databricks infrastructure state at once. You skip the headache of chunking or filtering cluster data before passing it to the agent. The integration maps directly to your existing Google Cloud workflows. If you already run BigQuery alongside your lakehouse, your agent can use `list_catalogs` and `list_schemas` to compare table structures across both platforms in a single prompt.

Enterprise Compute Auditing

Tracking expensive compute resources requires constant vigilance. Your Gemini agent takes over this workload by executing `list_clusters` and `list_warehouses` to pull real-time configurations. It reads the exact state of your Databricks environment without human intervention. You configure the connection using an McpToolset with StreamableHttpServerParameters. If you want to restrict what the agent can see, the ADK lets you apply a tool_names filter. This keeps the agent focused solely on compute metrics instead of wandering into job histories.

Automated Pipeline Tracking

Data pipelines break, and finding the root cause usually means digging through endless logs. A specialized Vertex AI agent can call `list_jobs` to identify failing workflows and immediately follow up with `list_job_runs` to grab the specific error states. The massive token limit means the agent can hold thousands of job run histories in memory simultaneously. It uses `get_cluster` to check if a specific node caused the failure, giving your engineering team a precise diagnosis instead of a vague alert.

Setup guide

Set up Databricks MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Databricks tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Databricks_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Databricks tools via MCP.",
    tools=mcp_tools,
)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Databricks. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Databricks now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Databricks MCP in Google ADK

Initialize an McpToolset using your Vinkius endpoint URL. Pass that toolset into the tools array of your LlmAgent constructor. The framework handles the HTTP transport automatically.

Yes. You can apply a tool names filter when setting up the toolset. This prevents the agent from calling endpoints like get_me if it only needs access to cluster data.

The massive Gemini context window handles large JSON payloads perfectly. Your agent can ingest the output of every job run in your lakehouse without dropping historical data.

The client supports both Stdio and HTTP transports for MCP tools. For Vinkius hosted endpoints, you will stick with the streamable HTTP configuration.

Your node types, warehouse sizes, and job run histories stay completely isolated. Vinkius provisions a single-use V8 sandbox that drops the connection the second your session ends, ensuring zero persistent storage of your infrastructure metadata.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript