How to Use the Carbonara MCP in AutoGen

Q: How do I configure Carbonara within an AutoGen agent group?

Use the autogen-extmcp package to load the Carbonara MCP tools. Pass the server URL to your AutoGen AssistantAgent so any agent in the group can call cookcodeimage.

Let your AutoGen agents debate, write, and render beautiful code images with Carbonara.

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 AutoGen

Create your Vinkius account to connect Carbonara to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Consensus-Driven Code Styling in AutoGen

Set up an AutoGen multi-agent debate where one agent writes the code and another reviews it before rendering with Carbonara. Once they agree, the assistant agent calls `cook_code_image` to create the final styled PNG. This collaborative AutoGen approach ensures that only working, syntactically correct code gets sent to the Carbonara server, preventing broken visual snippets in your output.

Automated Code Design via Multi-Agent Chats

Give your AutoGen design agent the power to style code blocks using Carbonara. The agent can invoke `cook_code_image` with custom window controls and themes to match your brand guidelines automatically. By separating code generation from visual styling, your AutoGen agents work in parallel to produce production-ready Carbonara graphics without manual intervention.

Connect AutoGen to the Carbonara MCP Server

Use the Streamable HTTP transport to link your AutoGen multi-agent conversation directly to the Carbonara MCP Server. The `cook_code_image` tool becomes available to any agent in your AutoGen group chat. The AutoGen adapter handles schema conversion behind the scenes, making it easy for agents to pass code snippets and get back clean base64 Carbonara image strings.

Setup guide

Set up Carbonara MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Carbonara tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Carbonara_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Carbonara data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Carbonara_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Carbonara data")
    print(result.messages[-1].content)

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 AutoGen

Use the autogen-ext[mcp] package to load the Carbonara MCP tools. Pass the server URL to your AutoGen `AssistantAgent` so any agent in the group can call `cook_code_image`.

Yes, an AutoGen reviewer agent can inspect the parameters sent to `cook_code_image` and ask the writer agent to adjust the Carbonara theme or syntax settings before final rendering.

It does, AutoGen agents receive the base64 PNG string in the Carbonara tool response, which they can then pass to other agents or save to the local disk.

Yes, you can run Carbonara locally or use our managed endpoint for AutoGen. The agents connect via standard MCP transports like HTTP or stdio without extra configuration.

We use ephemeral, zero-trust environments for all AutoGen requests. Your code snippets and generated images never touch persistent storage, keeping your proprietary logic completely private.

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