How to Use the Balena MCP in Google ADK

Q: How do I connect my Google ADK agent to Balena?

You'll use the McpToolset from the Google ADK library. Point it to your Vinkius server URL, and then add that toolset to your LlmAgent. The agent will then have access to all the Balena tools.

Q: Does the Google ADK support filtering which Balena tools are exposed?

Yes, the McpToolset constructor accepts a toolnames argument. This lets you create agents with limited permissions, which is a good practice for building secure, specialized agents on Google Cloud to manage your Balena fleet.

Connect Google's Gemini agents to your Balena IoT fleet. Query devices and trigger actions using the Google ADK and your GCP data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Balena MCP to Google ADK

Create your Vinkius account to connect Balena 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 Balena with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query Balena, Analyze in BigQuery

Pull your Balena device and fleet status directly into your Google-native workflow. Your Gemini agent can use `list_devices` and `list_fleets` to get real-time data from your IoT infrastructure. The OData filtering lets you be precise, so you're not pulling down everything at once. The real power comes when you combine this with Google's stack. Have your agent fetch device logs and statuses, then push that data into a BigQuery table for long-term analysis. The ADK makes bridging your Balena hardware and your Google data warehouse straightforward.

Manage Devices with Gemini's Long Context

Use Gemini's massive context window to reason about your entire fleet. Your agent can pull data on dozens of devices using `list_devices`, hold it all in context, and then make informed decisions. It can check who it's authenticated as with `whoami` to ensure correct permissions. This lets you ask complex questions. For example: "Find all raspberrypi3 devices in the 'production' fleet that haven't been updated in 30 days and create a tag for them." Your agent can chain `list_devices`, `list_releases`, and `create_device_tag` to get it done.

Integrate Balena into Vertex AI Pipelines

This MCP Server turns Balena into just another tool for your Vertex AI agents. You can build pipelines that react to events in your Google Cloud environment. A new model in Vertex AI? Have an agent automatically set a new `create_device_env_var` on your edge devices to point to it. Setup is clean. You instantiate an `McpToolset` with your Vinkius URL and pass it to your `LlmAgent`. You can even filter the `tool_names` to create agents with specific permissions, like a "read-only" agent for monitoring dashboards.

Setup guide

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

You'll use the `McpToolset` from the Google ADK library. Point it to your Vinkius server URL, and then add that toolset to your `LlmAgent`. The agent will then have access to all the Balena tools.

Absolutely. You can fetch large amounts of data from Balena using tools like `list_devices` and feed it all into your Gemini agent. This allows for complex, multi-step reasoning across your entire device fleet.

Yes, the `McpToolset` constructor accepts a `tool_names` argument. This lets you create agents with limited permissions, which is a good practice for building secure, specialized agents on Google Cloud to manage your Balena fleet.

If you're already in the Google Cloud ecosystem, it's a natural fit. The ADK is designed to work with BigQuery and Vertex AI, letting you build automations that combine your cloud data with your physical Balena devices.

The server accesses your Balena device and fleet configuration data, such as device UUIDs, fleet slugs, and environment variable names. All communication is routed through Vinkius's secure, ephemeral instances. Your actual Balena secrets stay out of the agent's code and Google's logs.

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