How to Use the Dog CEO MCP in OpenAI Agents SDK

Q: How do I connect the Dog CEO API to my OpenAI Agents SDK?

Install openai-agents and initialize MCPServerStreamableHttp pointing to the Vinkius URL. Pass this instance in the list of MCP servers when instantiating your Agent. The agent automatically registers listdogbreeds, getdogbybreed, and getrandomdogimage.

Q: Can I use OpenAI Agents SDK to filter Dog CEO breeds before calling the image tool?

Yes. Your agent can first call listdogbreeds to get the master list. It then uses that validated list to pick the correct parameter for getdogbybreed, preventing API errors from invalid breed names.

Q: Is caching supported for tool definitions in this setup?

Yes. Set cacheToolsList=True in your MCPServerStreamableHttpParams. This keeps the OpenAI Agents SDK from querying the Vinkius endpoint for tool definitions on every single run, speeding up tool execution.

Build reliable production agents that fetch live dog breed data and images with OpenAI Agents SDK.

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 OpenAI Agents SDK

Create your Vinkius account to connect Dog CEO to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Fetch raw breed data with OpenAI Agents SDK

Your agent needs clean data to make decisions. When you connect this MCP server, the agent runs `list_dog_breeds` to pull the current breed list. The OpenAI Agents SDK automatically maps this tool schema so your agent knows what to ask for without manual configuration. You get direct access to the live taxonomy. No hardcoded lists in your Python code that go out of date when a new sub-breed gets added. The agent fetches the exact structure it needs, when it needs it.

Run `get_dog_by_breed` inside your agent workflow

If your workflow requires visual confirmation, the agent triggers `get_dog_by_breed` to pull a targeted image. The OpenAI Agents SDK handles the tool execution loop, feeding the resulting URL back into the model context for immediate validation. This means your specialized visual agent can hand off the image URL to a processing agent. The built-in tracing on your OpenAI dashboard tracks the entire execution path from the initial tool call to the final output.

Randomize visual assets with this MCP Server

Sometimes you just need a random photo to keep users engaged. The agent calls `get_random_dog_image` to grab a random URL instantly. By setting `cacheToolsList=True` in your Python setup, the agent discovers this tool instantly on startup without lagging. The SDK manages the HTTP connection pool under the hood. Your runtime performance stays high because the agent doesn't waste overhead re-registering the schema on every single user request.

Setup guide

Set up Dog CEO MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Dog CEO tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Dog CEO tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Dog CEO tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Dog CEO Agent",
            instructions="You have access to Dog CEO tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install `openai-agents` and initialize `MCPServerStreamableHttp` pointing to the Vinkius URL. Pass this instance in the list of MCP servers when instantiating your Agent. The agent automatically registers `list_dog_breeds`, `get_dog_by_breed`, and `get_random_dog_image`.

Yes. Your agent can first call `list_dog_breeds` to get the master list. It then uses that validated list to pick the correct parameter for `get_dog_by_breed`, preventing API errors from invalid breed names.

The SDK relies on your configured agent guardrails and retry logic. If the Dog CEO endpoint throttles a `get_random_dog_image` request, the SDK handles the exception or triggers a fallback agent to retry the call.

Yes. Set `cacheToolsList=True` in your `MCPServerStreamableHttpParams`. This keeps the OpenAI Agents SDK from querying the Vinkius endpoint for tool definitions on every single run, speeding up tool execution.

This MCP server only processes public dog breed names and image URLs. It never touches personally identifiable information, and Vinkius runs the execution in an ephemeral, isolated environment to keep your session data secure.

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