How to Use the Cube.dev MCP in Google ADK

Q: How do I register the Cube.dev MCP Server in Google ADK?

You initialize McpToolset with your Vinkius HTTP endpoint URL. Pass this toolset object into your LlmAgent configuration. The Google ADK agent will immediately see all fifteen Cube tools.

Q: Can a Google ADK agent trigger Cube.dev pre-aggregations?

Yes, your agent can call triggerpreaggregationjob when it detects database updates. It then uses getpreaggregationjobstatus to monitor the build, ensuring your BigQuery data is cached and ready.

Q: How does Google ADK handle Cube.dev environment changes?

By using your CUBECLOUDAPIKEY, the agent queries listenvironments and listdeployments. This lets your Gemini agent dynamically switch targets depending on whether it is running tests or production tasks.

Q: Can I restrict which Cube.dev tools Google ADK can access?

Yes, you can use the toolnames filter when setting up your MCP toolset. This lets you restrict your Gemini agent to read-only tools like loadquery while blocking destructive actions.

Q: How does Google ADK protect my Cube.dev credentials?

Your CUBECLOUDAPIKEY and database credentials are never exposed to the LLM. They reside securely inside the Vinkius sandbox, where tools like generatemetatoken safely sign JWTs without exposing raw secrets.

Run complex data analysis across Cube.dev and BigQuery using Google ADK and Gemini's massive context window.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cube.dev MCP to Google ADK

Create your Vinkius account to connect Cube.dev 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 Cube.dev with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

BigQuery and Cube.dev sync via Google ADK

The `list_data_sources` tool keeps your cloud data warehouse and semantic layer aligned using this MCP Server. Your Google ADK agent calls it to identify active connections and maps them directly to your BigQuery datasets. The agent processes these schemas using Gemini's long context, running `load_query` to pull aggregated metrics. This bridges the gap between raw cloud storage and your structured semantic definitions.

Automated schema mapping for Gemini agents

This MCP Server exposes `list_entities` and `get_meta` so your agent can scan your entire Cube catalog in one go. Gemini needs to see the whole picture to write good queries. Because Gemini handles huge token limits, it digests the detailed payload from `get_entity` without choking. The agent builds a complete mental map of your cubes, ensuring it never hallucinates columns.

Real-time query conversion and validation

The `convert_query` tool translates raw SQL requests into Cube-compliant REST queries, validating them against your active environments. Stop guessing if your SQL works. To make sure everything runs fine, the agent calls `get_sql` to review the compiled SQL. This gives your Google Cloud pipelines a clean, automated way to verify queries before they hit production.

Setup guide

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

You initialize `McpToolset` with your Vinkius HTTP endpoint URL. Pass this toolset object into your `LlmAgent` configuration. The Google ADK agent will immediately see all fifteen Cube tools.

Yes, your agent can call `trigger_pre_aggregation_job` when it detects database updates. It then uses `get_pre_aggregation_job_status` to monitor the build, ensuring your BigQuery data is cached and ready.

By using your CUBE_CLOUD_API_KEY, the agent queries `list_environments` and `list_deployments`. This lets your Gemini agent dynamically switch targets depending on whether it is running tests or production tasks.

Yes, you can use the `tool_names` filter when setting up your MCP toolset. This lets you restrict your Gemini agent to read-only tools like `load_query` while blocking destructive actions.

Your CUBE_CLOUD_API_KEY and database credentials are never exposed to the LLM. They reside securely inside the Vinkius sandbox, where tools like `generate_meta_token` safely sign JWTs without exposing raw secrets.

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