How to Use the ClassPass MCP in Google ADK

Q: How do I use Google ADK to query my ClassPass schedule?

Instantiate an McpToolset with your Vinkius server URL and pass it to your LlmAgent in the tools list. Your Gemini agent can then invoke the listschedule tool to get the data.

Q: Can I combine ClassPass performance data with my own data using Google ADK?

Absolutely. A Gemini agent can call getperformance, then use native Google ADK tools to push that data into BigQuery. This allows you to analyze your ClassPass metrics against your existing enterprise datasets.

Q: Does Google ADK support all the ClassPass MCP tools?

Yes, it discovers and can use all available tools, from getclassdetail to getperformance. You can also use the toolnames filter to restrict an agent's access to specific tools for security.

Connect Gemini to your ClassPass data and analyze it alongside your enterprise data with 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 ClassPass MCP to Google ADK

Create your Vinkius account to connect ClassPass 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 ClassPass with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

ClassPass Data, Meet BigQuery

This is how you get your ClassPass data into your Google Cloud ecosystem. Have a Gemini agent call `get_performance` to fetch your latest venue analytics right from the source. From there, the agent can use native Google ADK tools to pipe that data directly into a BigQuery table or trigger a Vertex AI pipeline. It’s the fastest way to combine your ClassPass operational data with the rest of your business intelligence stack.

Manage Your Venue with a Massive Context

Gemini's huge context window changes how you can work. Your agent can pull the entire schedule with `list_schedule`, all reservations with `list_reservations`, and inventory with `list_inventory`, then hold all of it in its context at once. This lets you ask complex, multi-step questions without the agent losing track. You can ask things like, "Compare attendance from last month's reservations to this month's schedule and tell me which classes have open SmartSpots." The agent will just figure it out.

Connect Google ADK to the ClassPass MCP Server

Getting started is simple. You wrap your Vinkius URL in an `McpToolset` and pass it into your `LlmAgent`. Google ADK handles the rest, automatically discovering the available ClassPass tools. For enterprise environments, you can use the `tool_names` filter to limit which tools an agent can access. This lets you build specialized agents that, for example, only have permission to read performance data with `get_performance` but can't see reservation details.

Setup guide

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

Instantiate an `McpToolset` with your Vinkius server URL and pass it to your `LlmAgent` in the `tools` list. Your Gemini agent can then invoke the `list_schedule` tool to get the data.

Absolutely. A Gemini agent can call `get_performance`, then use native Google ADK tools to push that data into BigQuery. This allows you to analyze your ClassPass metrics against your existing enterprise datasets.

Gemini's long context is ideal for this. Your agent can call `list_locations` to get all your venues, then run `list_schedule` or `list_reservations` for each one, all within a single, coherent session.

Yes, it discovers and can use all available tools, from `get_class_detail` to `get_performance`. You can also use the `tool_names` filter to restrict an agent's access to specific tools for security.

Vinkius secures the connection from end to end. Your requests are authenticated with a token and executed inside an isolated sandbox that's destroyed after the call. The MCP server only handles your venue's reservation and schedule data, and never stores it.

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