How to Use the Mariana Tek MCP in Google ADK

Q: How do I initialize Mariana Tek in Google ADK?

Use the McpToolset class with StreamableHttpServerParameters. Pass the resulting object into your LlmAgent under the tools parameter.

Q: Can Google ADK handle multiple Mariana Tek locations?

Yes. The agent calls listlocations to get the studio IDs. It then filters subsequent listclasses requests by those specific location IDs.

Q: Does the Mariana Tek MCP Server support BigQuery workflows in Google ADK?

Yes. Your agent can fetch live pricing via listpricing and instantly compare it against historical sales data stored in your Google Cloud data warehouse.

Q: How do I limit which tools the MCP Server exposes?

Pass an optional toolnames filter when setting up the toolset. You can restrict the agent to just getclassdetail and listclasstypes if you only want it answering schedule questions.

Q: What happens to Mariana Tek profile data during an MCP Server query?

When your agent calls getcustomer to read credit balances, the payload routes through a secure, single-use Vinkius endpoint token. The execution environment is completely ephemeral, leaving zero trace of member profiles.

Connect Mariana Tek to Google ADK. Feed studio schedules and member data into Gemini for long-context enterprise reasoning.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mariana Tek MCP to Google ADK

Create your Vinkius account to connect Mariana Tek 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 Mariana Tek with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze studio data with Google ADK

The server connects your fitness operations directly to Gemini. Your agent runs `list_classes` and `list_instructors` to pull the entire week's schedule into context. Because Google ADK supports massive context windows, you can dump thousands of class records into a single prompt. Gemini cross-references this raw schedule data against your existing BigQuery analytics.

Audit member reservations at scale

Customer discovery happens through the `search_customers` and `get_customer` tools. Your agent pulls visit counts, active credits, and membership status in one go. You then execute `list_reservations` to map out attendance patterns. Passing this data through Vertex AI lets you build churn-prediction models based entirely on real-time studio activity.

Sync pricing across an MCP Server

Querying `list_pricing` retrieves current promotional rates and corporate packages. The agent pairs this with `list_memberships` to build a complete picture of your revenue options. You restrict exposed endpoints using the `tool_names` filter in the `McpToolset` setup. This keeps your Google Cloud agents focused strictly on sales data rather than getting distracted by `list_locations`.

Setup guide

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

Use the `McpToolset` class with `StreamableHttpServerParameters`. Pass the resulting object into your `LlmAgent` under the `tools` parameter.

Yes. The agent calls `list_locations` to get the studio IDs. It then filters subsequent `list_classes` requests by those specific location IDs.

Yes. Your agent can fetch live pricing via `list_pricing` and instantly compare it against historical sales data stored in your Google Cloud data warehouse.

Pass an optional `tool_names` filter when setting up the toolset. You can restrict the agent to just `get_class_detail` and `list_class_types` if you only want it answering schedule questions.

When your agent calls `get_customer` to read credit balances, the payload routes through a secure, single-use Vinkius endpoint token. The execution environment is completely ephemeral, leaving zero trace of member profiles.

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