How to Use the Carbonara MCP in OpenAI Agents SDK

Q: How do I connect Carbonara to the OpenAI Agents SDK?

Initialize the MCP Server using MCPServerStreamableHttp with your Vinkius endpoint. Pass it to the Agent constructor via the mcpservers array. Set cacheToolsList=True to speed up initialization.

Turn raw code into beautiful syntax-highlighted PNGs directly from your OpenAI Agents SDK production workflows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Carbonara MCP to OpenAI Agents SDK

Create your Vinkius account to connect Carbonara 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 Carbonara with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Visual Code Generation via MCP Server

Your production agent needs to share code visually by generating styled images without breaking safety constraints. Connecting this MCP Server to your setup lets the agent create these graphical assets instantly. Calling `cook_code_image` returns a base64 encoded PNG right into the context window. The OpenAI dashboard traces the exact inputs sent to the renderer, ensuring no sensitive logic leaks during the visual transformation.

Guardrailed Image Generation

You don't want raw strings hitting external rendering APIs without oversight. You configure the agent with strict validation rules before it ever formats the payload. The system automatically discovers the image tool upon initialization. Once the built-in guardrails clear the request, the agent applies custom themes and window controls to create the final asset.

Handoff-Ready Visual Assets

Specialized agents handle specific tasks in a deployed pipeline. A documentation agent writes the explanation, then hands off the actual snippet to a rendering agent. That second agent uses the tool to generate the visual representation. The base64 output flows straight into your final markdown or HTML build process without manual intervention.

Setup guide

Set up Carbonara 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 Carbonara tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Carbonara 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="Carbonara Agent",
            instructions="You have access to Carbonara 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 Carbonara. 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 Carbonara 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 Carbonara MCP in OpenAI Agents SDK

Initialize the MCP Server using `MCPServerStreamableHttp` with your Vinkius endpoint. Pass it to the Agent constructor via the `mcp_servers` array. Set `cacheToolsList=True` to speed up initialization.

Yes. You build guardrails that check the code snippet before the agent executes the tool. This prevents bad formatting or sensitive data from reaching the renderer.

The tool accepts theme parameters directly. Your agent decides which colors and window controls match your brand guidelines when making the request.

Standard text outputs fail when you need to embed code in social media or slide decks. This server returns a base64 PNG that you can instantly save or upload.

The Vinkius V8 isolate sandbox destroys the environment immediately after generating the image. Your proprietary algorithms never persist on disk, and the ephemeral token expires instantly.

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