How to Use the Arbox MCP in Google ADK

Q: How do I add the Arbox server to a Google ADK agent?

You'll instantiate an McpToolset and point it to your Vinkius server URL using StreamableHttpServerParameters. Then, you pass that toolset into the tools list when creating your LlmAgent.

Q: I only want my Google ADK agent to see the schedule and coaches from Arbox. Is that possible?

Yes. When you configure the McpToolset for Arbox in your Google ADK code, you can use the toolnames filter. Just pass a list containing 'listschedule' and 'listcoaches' to restrict the agent's access.

Q: How does a Gemini agent in Google ADK handle finding a specific member in Arbox?

It will use the searchmembers tool. Thanks to Gemini's reasoning capabilities, you can ask a complex question in natural language, and the agent will know to use that tool to find the right person and their associated data.

Let your Gemini-powered Google ADK agent query Arbox data and analyze it alongside your Google Cloud datasets.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Arbox MCP to Google ADK

Create your Vinkius account to connect Arbox 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 Arbox with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query Arbox from Google Cloud

This server connects your Arbox studio data directly into your Google Cloud environment. Your Google ADK agent can use `list_memberships` to pull all your plans or `list_payments` to get transaction histories. It's the missing link between your fitness studio's operations and your enterprise data warehouse. The real power comes when you combine this with your own data. Have your agent pull leads with `list_leads`, then cross-reference them with marketing campaign data you already have in BigQuery. Gemini's long-context window means your agent can reason over massive amounts of combined data.

Build an Enterprise Agent on Google ADK

Use Google's agent framework to build serious business tools. Your agent can monitor studio operations by calling `list_schedule` for class capacity or `list_coaches` to check staffing. You can filter the tools exposed to the agent using the `tool_names` parameter for more control. This isn't just a chatbot. It's an agent that lives in your Google Cloud project. You can set it up to run on a schedule, trigger it from a Cloud Function, and have it report its findings back to a Vertex AI pipeline. This MCP server makes Arbox a first-class citizen in that ecosystem.

Deep Member & Sales Analysis

Go beyond simple lookups. The `search_members` tool gives your agent a member's profile, attendance history, and a calculated engagement score. Your Gemini agent can take that data and perform complex analysis without you writing a single line of SQL. For example, ask your agent to 'find all members with a low engagement score who are on the premium plan and haven't attended a class in 3 weeks.' The agent will use `search_members` and `get_member` to get the data, then use the model's reasoning to give you a precise list.

Setup guide

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

You'll instantiate an `McpToolset` and point it to your Vinkius server URL using `StreamableHttpServerParameters`. Then, you pass that toolset into the `tools` list when creating your `LlmAgent`.

Absolutely. That's a primary use case. Your agent can call the `list_leads` tool on the Arbox MCP server and then use native Google Cloud tools to query BigQuery, all within the same chain of thought.

Yes. When you configure the `McpToolset` for Arbox in your Google ADK code, you can use the `tool_names` filter. Just pass a list containing 'list_schedule' and 'list_coaches' to restrict the agent's access.

It will use the `search_members` tool. Thanks to Gemini's reasoning capabilities, you can ask a complex question in natural language, and the agent will know to use that tool to find the right person and their associated data.

The server only accesses the Arbox data you ask for, like member profiles or payment lists. Vinkius secures the connection with a unique token for your endpoint. The compute environment is isolated and ephemeral, meaning the container running the logic is torn down after your request is complete.

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