How to Use the Databox MCP in Google ADK

Q: How do I initialize Databox inside Google ADK?

Install google-adk and wrap the Vinkius URL in StreamableHttpServerParameters. Pass that into the McpToolset and hand it to your LlmAgent. The tools register instantly.

Q: Can Google ADK filter which Databox tools the agent sees?

Yes. You can use the toolnames filter when setting up the toolset. This prevents the model from accessing destructive actions like deletedataset if it only needs read access.

Q: How do I inspect a specific metric container?

Have the agent execute getdatasetdetails with the target ID. It returns the schema, dimensions, and configuration for that specific group of metrics.

Give your Gemini agents the ability to read and write Databox metrics natively via this MCP Server using Google ADK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Databox MCP to Google ADK

Create your Vinkius account to connect Databox 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 Databox with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze datasets with Google ADK

Using `list_dataset_metrics` allows your agent to pull thousands of rows and dump them straight into Gemini's massive context window. You don't even need to chunk the payload. Connecting this MCP Server to your Google Cloud environment links your dashboards to your data warehouse. You can write scripts where an agent reads BigQuery tables and immediately fires `push_metrics_data` to update your live KPIs.

Map organizational data sources

Running `list_accounts` lets your Gemini agent index every connected profile across your messy enterprise deployments. It maps the exact structure of your analytics setup. Managing those connections is just as easy. If a new Vertex AI pipeline needs a tracking endpoint, the agent simply calls `create_data_source` to provision it automatically.

Monitor API consumption

Triggering `get_storage_statistics` daily via an autonomous MCP routine alerts your team before high-volume ingestion eats through your quota. You get hard numbers on your usage. Security teams love audit trails. Firing `list_activity_logs` pulls the exact history of who touched what, which Gemini can then parse to detect unusual access patterns.

Setup guide

Set up Databox 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 Databox 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="Databox_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Databox 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 Databox. 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 Databox 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 Databox MCP in Google ADK

Install `google-adk` and wrap the Vinkius URL in `StreamableHttpServerParameters`. Pass that into the `McpToolset` and hand it to your `LlmAgent`. The tools register instantly.

Yes. You can use the `tool_names` filter when setting up the toolset. This prevents the model from accessing destructive actions like `delete_dataset` if it only needs read access.

The connection relies on HTTP transport. Google's framework handles the routing between your Gemini agent and the Vinkius endpoint natively.

Have the agent execute `get_dataset_details` with the target ID. It returns the schema, dimensions, and configuration for that specific group of metrics.

Your raw KPI numbers and dataset schemas remain private. Vinkius routes the data through a zero-trust, ephemeral sandbox. The connection requires only a single endpoint token, keeping your core credentials isolated from the model.

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