How to Use the Amenitiz MCP in Pydantic AI

Q: How does Pydantic AI connect to the Amenitiz MCP server?

It's a one-liner. You instantiate an MCPToolset with the Vinkius server URL and pass it to your Pydantic AI Agent. The framework handles the rest, including fetching the tool definitions.

Q: What happens if the Amenitiz API changes unexpectedly with Pydantic AI?

Your Pydantic AI agent will fail loudly with a ValidationError. This is a feature, not a bug. It prevents your agent from working with malformed data that could cause silent errors downstream.

Get type-safe, validated hotel data from Amenitiz in any Python agent with 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 Amenitiz MCP to Pydantic AI

Create your Vinkius account to connect Amenitiz 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 Amenitiz with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

No More Bad Data. Period.

When your agent calls `get_reservation`, Pydantic AI validates the entire response against a Pydantic model. If the Amenitiz API ever returns a null where a string should be, your code will raise a `ValidationError` instantly. This stops data corruption before it starts. You don't have to write endless `if/else` checks for every field. You can trust that the data object your agent receives is exactly what you expect it to be.

Reliable Checks for Rates & Rooms

Build internal tools with confidence. Your agent can query room details with `list_room_types` and current pricing with `get_rates`, and you'll know the data is correct. Because Pydantic AI enforces the data schema, your agent won't crash from an unexpected change in the source API. It's perfect for building things like nightly reports or financial summaries where correctness is the only thing that matters.

A Model-Agnostic Amenitiz MCP Server

Use this Amenitiz toolset with any LLM. Pydantic AI is model-agnostic, so you can call `list_guests` using an OpenAI model, then swap to a local Llama model for testing. The tool works the same. The validation layer is separate from the LLM. This protects your agent's logic from any weird formatting the model might introduce. The MCP server provides the tools, and Pydantic AI ensures they return clean data every time.

Setup guide

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

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

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

It's a one-liner. You instantiate an `MCPToolset` with the Vinkius server URL and pass it to your Pydantic AI `Agent`. The framework handles the rest, including fetching the tool definitions.

Your Pydantic AI agent will fail loudly with a `ValidationError`. This is a feature, not a bug. It prevents your agent from working with malformed data that could cause silent errors downstream.

Yes. While the MCP server exposes all eight tools, you can configure the `Agent` in Pydantic AI to only use a subset, like just `get_availability` and `get_rates` for a pricing bot.

It's not about speed, it's about correctness. The validation adds a tiny bit of overhead, but it saves you from hours of debugging silent data corruption bugs. For code that has to be right, it's the only way to go.

The data flow is secure and stateless. Your agent calls a tool like `list_guests`, and the data is streamed from Amenitiz, through the Vinkius temporary sandbox, and directly to your client. No guest records or reservation details are ever persisted on Vinkius servers.

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