How to Use the Demio MCP in Pydantic AI

Q: How does Pydantic AI work with the Demio MCP server?

You create an MCPToolset instance with your Vinkius server URL and pass it to your Pydantic AI Agent. The framework handles calling the tools and, most importantly, validates every single response against a Pydantic model.

Q: What happens if the Demio API changes and my Pydantic AI agent gets unexpected data?

Your agent will raise a ValidationError. This is the core benefit of Pydantic AI—it prevents malformed data from being processed by your application. You'll know instantly that the API response doesn't match the expected schema.

Q: Can I use Pydantic AI to register users for a Demio webinar?

Yes, your agent will use the registeruserforwebinar tool. The framework helps ensure that the data you provide for the user, like their name and email, is correctly structured before it's sent to the Demio API.

Build type-safe Demio agents with Pydantic AI. Get validated webinar data you can trust in your Python application.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Demio MCP to Pydantic AI

Create your Vinkius account to connect Demio 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 Demio with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Get Schema-Validated Demio Data

This toolset lets your agent pull data from Demio with confidence. When your agent calls `get_webinar_details` or `get_session_details`, Pydantic AI automatically validates the response against a strict schema. If Demio's API ever returns an unexpected field or a wrong data type, your agent won't guess or fail silently. It will raise a `ValidationError`, so you know immediately that the data isn't what you expected. No more corrupted data making it into your system.

Manage Webinars with Pydantic AI

Build reliable workflows for managing your Demio events. Your agent can `list_upcoming_webinars` and `list_webinar_registrants`, and you'll get back clean, typed Python objects every time. Even actions are safer. When you use `register_user_for_webinar`, Pydantic AI helps ensure the inputs are correctly formatted before the call is even made. It's all about catching errors early.

Build a Reporting Agent with any LLM

Use this MCP Server to build a reporting bot that works with any major LLM. Pydantic AI is model-agnostic, so you can point it at OpenAI, Anthropic, Gemini, or even a local model. Have your agent `get_webinar_report` for a completed event, and the structured response is guaranteed. This makes it simple to build reliable tools that summarize webinar performance, no matter which AI model is driving the agent.

Setup guide

Set up Demio 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": {
        "demio-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Demio 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 Demio. 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 Demio 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 Demio MCP in Pydantic AI

You create an `MCPToolset` instance with your Vinkius server URL and pass it to your Pydantic AI `Agent`. The framework handles calling the tools and, most importantly, validates every single response against a Pydantic model.

Your agent will raise a `ValidationError`. This is the core benefit of Pydantic AI—it prevents malformed data from being processed by your application. You'll know instantly that the API response doesn't match the expected schema.

Yes, your agent will use the `register_user_for_webinar` tool. The framework helps ensure that the data you provide for the user, like their name and email, is correctly structured before it's sent to the Demio API.

Pydantic AI is model-agnostic. You can use this Demio toolset with agents powered by OpenAI, a local Llama model via Ollama, or anything in between. The tool-calling and validation logic is completely separate from the LLM.

This server processes webinar registrant details, such as names and emails. Your Vinkius endpoint authenticates every request. The MCP server itself is stateless and runs in an ephemeral V8 Isolate, ensuring your data is only used for the immediate transaction and not stored.

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