How to Use the ezyVet MCP in Pydantic AI

Ensure type-safe clinical data handling with Pydantic AI and the ezyVet 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 ezyVet MCP to Pydantic AI

Create your Vinkius account to connect ezyVet 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 ezyVet with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe veterinary records

Every response from `get_animal` or `get_consult` is validated against your Pydantic models. If the API returns garbage, your agent throws an error immediately. This prevents bad data from poisoning your logic. You know exactly what the shape of the record is before your code touches it.

Strict financial record validation

Use `list_invoices` to pull billing data into your agent safely. Pydantic AI checks every field, ensuring your financial reporting remains accurate. Errors in billing are expensive. This approach catches discrepancies at the agent level before they ever reach your final output.

Reliable contact management

Fetch client details using `list_contacts` with full schema enforcement. Your agent relies on validated types for every interaction. It is the safest way to build. You do not worry about missing fields or unexpected data types when processing your client list.

Setup guide

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

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

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

You define your Pydantic schemas to match the expected output of the ezyVet tools. The MCP server provides the data, and your models handle the validation.

Yes, and that is by design. It stops the execution to prevent silent errors, forcing you to address the data issue immediately.

It is model-agnostic. Whether you use local models or external APIs, the server provides the same consistent, validated stream of data.

It supports SSE and Streamable HTTP. You simply pass the endpoint to the MCPToolset and let the framework handle the handshake.

Your data is validated in memory and never stored by the server. We keep the pipeline clean by ensuring that only authorized, typed data passes through the agent.

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