How to Use the Dog CEO MCP in Pydantic AI

Q: How do I register the Dog CEO toolset in Pydantic AI?

Install the package with the MCP extra, then instantiate MCPToolset with the Vinkius URL. Pass this object to your Agent via the toolsets parameter to instantly register all three dog tools.

Q: How does the Dog CEO integration handle deprecated HTTP classes in Pydantic AI?

Use the unified MCPToolset constructor pointing to your Vinkius HTTP endpoint. The older MCPServerHTTP class is deprecated, and the unified approach ensures clean, type-safe connections.

Enforce strict runtime type-safety on dog breed data and image retrieval using 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 Dog CEO MCP to Pydantic AI

Create your Vinkius account to connect Dog CEO 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 Dog CEO with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run `list_dog_breeds` with Pydantic AI validation

If your Python application demands absolute data integrity, you cannot rely on loose JSON responses. When your agent calls `list_dog_breeds`, the runtime validates the returned breed structure against strict Pydantic models before your code ever touches it. This means if the API schema changes unexpectedly, your system raises a clear validation error immediately. No silent failures, no malformed data corrupting your downstream logic.

Fetch structured dog images via MCP Server

When calling `get_dog_by_breed`, you want to be sure the return payload is a valid URL string. Pydantic AI parses the tool response, verifying the image URL structure at runtime. If the model attempts to pass an invalid breed parameter, the tool execution fails gracefully with clear validation logs. This level of type safety ensures your production pipelines remain completely predictable.

Type-safe random image retrieval using Pydantic AI

Get random visual assets using `get_random_dog_image` without worrying about schema drift. The unified toolset client connects to the MCP server, handles the HTTP transport, and enforces type validation on the response. This works whether you are running OpenAI, Anthropic, or local models. The validation layer sits at the framework level, ensuring consistent, typed data regardless of which LLM provider you use.

Setup guide

Set up Dog CEO 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": {
        "dog-ceo-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

Install the package with the MCP extra, then instantiate `MCPToolset` with the Vinkius URL. Pass this object to your `Agent` via the `toolsets` parameter to instantly register all three dog tools.

Yes. The framework intercepts the tool response from the Dog CEO MCP server and validates the data structure. If the API returns a malformed image URL, Pydantic AI raises a validation error instead of letting your agent consume bad data.

Use the unified `MCPToolset` constructor pointing to your Vinkius HTTP endpoint. The older `MCPServerHTTP` class is deprecated, and the unified approach ensures clean, type-safe connections.

Yes. Because Pydantic AI is model-agnostic, you can connect this toolset to local models running via Ollama or any other provider, while maintaining the same strict runtime validation.

This MCP server only reads public dog breed names and image URLs. Pydantic AI validates these strings locally, and Vinkius runs the actual MCP server in a zero-trust, ephemeral sandbox to keep your runtime environment isolated.

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