How to Use the ClassPass MCP in Pydantic AI

Q: How does Pydantic AI ensure my ClassPass data is correct?

When your agent calls a tool like listreservations, Pydantic AI validates the server's JSON response against a predefined schema. If there's any mismatch, it raises a ValidationError instead of passing bad data to your application.

Q: How do I add the ClassPass tools to my agent using Pydantic AI?

Create an MCPToolset instance with your Vinkius server URL and include it in the toolsets list when you initialize your Pydantic AI Agent. The framework handles the discovery and validation.

Build reliable agents that access your ClassPass data with the type-safe validation of Pydantic AI.

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 Pydantic AI

Create your Vinkius account to connect ClassPass to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe ClassPass Operations

This is about getting correct data, every time. When your agent calls `list_reservations` or `get_class_detail`, Pydantic AI automatically validates the server's response against a strict Pydantic model. If the data doesn't match the expected schema, you get an immediate `ValidationError`. This approach stops silent data corruption before it starts. Your agent won't hallucinate fields or misinterpret the data from the ClassPass tools because it can't. You can trust that the data structure you're working with is always what you expect.

Use Any LLM with Your ClassPass Data

Pydantic AI isn't locked into one model provider. You can build an agent that uses the `get_performance` tool with an OpenAI model, then switch to a local Llama model tomorrow without rewriting your tool-handling logic. The `MCPToolset` abstracts the connection to this server. Your code for calling `list_schedule` or `list_inventory` stays exactly the same, no matter which large language model is powering your agent's reasoning.

Connect to this MCP Server with Pydantic AI

The setup is clean and minimal. Just `pip install "pydantic-ai-slim[mcp]"` and then point the `MCPToolset` at your Vinkius URL. It's a single line of code. You pass that toolset into your `Agent`'s constructor, and it's ready to go. The MCP integration supports both streaming and standard HTTP transports, so it fits into whatever architecture you're building. It's a simple way to add powerful, validated tools to your agent.

Setup guide

Set up ClassPass MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "classpass-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to ClassPass tools.",
)

result = await agent.run("List recent ClassPass transactions")
print(result.output)

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 Pydantic AI

When your agent calls a tool like `list_reservations`, Pydantic AI validates the server's JSON response against a predefined schema. If there's any mismatch, it raises a `ValidationError` instead of passing bad data to your application.

Yes. Pydantic AI is model-agnostic. You can connect it to the ClassPass MCP Server and use any supported LLM, whether it's from a major provider or one running on your own machine.

Create an `MCPToolset` instance with your Vinkius server URL and include it in the `toolsets` list when you initialize your Pydantic AI `Agent`. The framework handles the discovery and validation.

Your agent will fail loudly with a validation error. This is a core feature. It prevents your application from processing incorrectly structured data from tools like `get_performance`.

It is. Your agent communicates with the MCP server through a connection secured by Vinkius. All access to your venue's inventory and schedule data is authenticated by your token, and the sandboxed environment that processes the request is wiped clean after each use.

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