How to Use the Cat Facts MCP in Pydantic AI

Q: How does Pydantic AI work with the Cat Facts MCP Server?

You use the MCPToolset class, passing it your Vinkius server URL. Add this toolset to your agent, and it will automatically validate any data returned by the Cat Facts tools against Pydantic models.

Q: What happens if the Cat Facts API changes and breaks my Pydantic AI agent?

Your agent will fail loudly by raising a ValidationError. This is a feature, not a bug. It prevents your agent from processing incorrect data and forces you to update your models to match the new API structure.

Q: Should I use the old MCPServerHTTP class?

No, that class is deprecated. You should use the unified MCPToolset("http://...") approach, which supports all the latest features and transport methods.

Get type-safe cat facts in Python. Pydantic AI validates every response so your agent never works with bad data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cat Facts MCP to Pydantic AI

Create your Vinkius account to connect Cat Facts 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 Cat Facts with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Get Structured, Validated Breed Lists

When your agent calls `list_cat_breeds`, it doesn't just get a string of text. Pydantic AI automatically parses the response from this MCP Server and validates it against a Pydantic model. You get a clean Python list, ready to use. Here's the key: if the server ever returns malformed data or an unexpected format, your code doesn't guess. It raises a `ValidationError` immediately. This stops data corruption before it starts.

Fail-Safe Fact Generation

Calling `get_random_cat_fact` is a safe operation. Pydantic AI intercepts the JSON response from the server and ensures it matches your expected schema before your agent's code ever touches it. This means no more defensive coding to handle weird API outputs. If the data isn't a clean string as expected, you'll know right away. It makes your agent's logic simpler and far more reliable.

Model-Agnostic MCP Server Access

Pydantic AI doesn't care which LLM you use. You can power your agent with models from OpenAI, Anthropic, Google, or a local model running on your machine. The Cat Facts MCP Server will work the same way with all of them. The `MCPToolset` provides a standard way to connect to any MCP Server. Your agent calls `list_cat_facts`, and Pydantic AI handles the communication and validation, giving you structured data you can trust, regardless of the underlying model.

Setup guide

Set up Cat Facts 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": {
        "cat-facts-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

You use the `MCPToolset` class, passing it your Vinkius server URL. Add this toolset to your agent, and it will automatically validate any data returned by the Cat Facts tools against Pydantic models.

Your agent will fail loudly by raising a `ValidationError`. This is a feature, not a bug. It prevents your agent from processing incorrect data and forces you to update your models to match the new API structure.

Yes. Pydantic AI is model-agnostic, so you can connect it to any LLM that you can run locally. The `MCPToolset` handles the connection to the Cat Facts server independently.

No, that class is deprecated. You should use the unified `MCPToolset("http://...")` approach, which supports all the latest features and transport methods.

The server only has access to the non-sensitive data within your requests, like asking for a random fact or a list of breeds. Each request to the Vinkius-managed server runs in a new, isolated container that is immediately destroyed after the response is sent. No data from your Pydantic AI application is ever logged or 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