How to Use the Hostfully MCP in Pydantic AI

Q: How do I set up the Hostfully toolset in Pydantic AI?

Install the package using pip install "pydantic-ai-slimmcp". Use the unified MCPToolset constructor with your Vinkius HTTP URL and pass it to your agent's toolsets parameter.

Q: Can I use different LLM providers with this Hostfully setup?

Yes, the framework is model-agnostic. You can run listleads with Claude, switch to GPT-4 for heavy analysis, or use local models for simple property checks.

Run type-safe property management workflows with Pydantic AI and strict runtime schema validation.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Hostfully MCP to Pydantic AI

Create your Vinkius account to connect Hostfully 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 Hostfully with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe lead ingestion with Pydantic AI

Your agent calls `list_leads` to pull incoming booking requests and validates the structural types at runtime. If the Hostfully payload contains an unexpected field or a missing parameter, the framework fails immediately. Pydantic AI prevents silent data corruption before any booking update runs. You can trust that calls to `get_lead` match your internal models perfectly, keeping your pipeline clean.

Validate provider dispatch via MCP Server

We use `list_service_providers` to fetch vendor details and verify their contact records against strict schemas. This ensures your system never attempts to dispatch a cleaner with incomplete insurance or contact info. Using this MCP Server with type-safe agents means every reservation and booking is checked. The model validates the output of `list_guests` against your predefined schemas before sending automated check-in details.

Model-agnostic operations for Hostfully

You pull agency configurations using `list_agencies` and `get_agency` through our MCP interface without being locked into a single LLM provider. Pydantic AI works across OpenAI, Anthropic, or local models while maintaining strict schema enforcement. This flexibility lets you swap models based on task complexity. Use a fast, cheap model for listing properties via `list_properties` and a smart model for handling complex owner questions from `list_owners`.

Setup guide

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

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

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

Install the package using `pip install "pydantic-ai-slim[mcp]"`. Use the unified `MCPToolset` constructor with your Vinkius HTTP URL and pass it to your agent's `toolsets` parameter.

The library validates all incoming data against strict schemas. If a tool like `get_property` returns unexpected nulls or modified fields from Hostfully, the runner raises a loud error to prevent bad writes.

Yes, the framework supports both Streamable HTTP and SSE. You can connect your agent to our hosted endpoint without running any local node infrastructure.

Yes, the framework is model-agnostic. You can run `list_leads` with Claude, switch to GPT-4 for heavy analysis, or use local models for simple property checks.

Your guest profiles, agency details, and booking logs are processed inside secure, isolated V8 sandboxes. We handle authentication seamlessly, ensuring your operational tokens are never exposed to the underlying models.

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