How to Use the Guesty MCP in Pydantic AI

Build type-safe vacation rental agents using Pydantic AI and the Guesty MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Guesty MCP to Pydantic AI

Create your Vinkius account to connect Guesty 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 Guesty with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Reservation and Guest Tracking

Your agent fetches booking records via `get_reservation` and validates the schema against your Pydantic models at runtime. It checks guest profiles using `list_guests` to ensure all contact fields match your application's strict type definitions. If the API returns unexpected null values or altered data structures, the framework raises a validation error immediately. This strict validation prevents your agent from acting on corrupt booking data or sending broken details to guests.

Reliable Financial Auditing with Pydantic AI

Financial auditing relies on `get_owner_revenue` and `get_accounting_stats` to pull precise payout figures. The framework validates every expense, commission, and gross revenue field before your agent compiles the owner statements. This setup guarantees that your financial calculations are backed by strict Python types. You don't have to worry about silent type casting errors or hallucinated currency values slipping into your monthly reports.

Strict Operational Task Management

Maintenance workflows stay organized when the agent calls `list_tasks` and maps the results to your internal scheduling schemas. It verifies calendar availability using `get_calendar` to ensure tasks do not overlap with active bookings. The agent matches cleaning requirements with property specs retrieved from `get_listing`. If a property lacks expected metadata, the validation layer catches it, letting you fix the listing before dispatching staff.

Setup guide

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

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

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

You instantiate the MCPToolset with your server's HTTP endpoint URL. Pass this toolset directly into the agent's constructor. The framework handles the connection and exposes the tools to your model.

The framework raises a ValidationError at the exact moment the tool response arrives. Your code catches this error immediately, stopping the agent from executing further steps with bad data. This ensures high reliability in production.

Yes, you can define a Pydantic model for message objects and validate the output of `list_messages`. This ensures that guest names, email addresses, and message bodies conform to your expected formats before processing.

The framework relies on your HTTP client's transport layer to handle retries and backoffs. If the API returns a rate limit error, the tool call fails gracefully, allowing your agent's error-handling logic to reschedule the task.

All API calls are routed through Vinkius's zero-trust sandboxed environment. The server handles task lists, calendars, and listing details in memory without persistent logs. This keeps your operational schedules and property databases completely private.

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