How to Use the Carbonara MCP in LangChain

Q: Does LangSmith trace the Carbonara image data sent from LangChain?

It does. Every time your LangChain agent runs cookcodeimage via MCP, the input code and output base64 string show up in your LangSmith dashboard for easy debugging.

Get beautiful code images directly from your LangChain agent runs 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 LangChain

Create your Vinkius account to connect Carbonara to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Code Carbonara Rendering in LangChain Runs

Your LangChain agent can now instantly convert raw string outputs into clean, styled images. By hooking the `cook_code_image` tool directly into your chain, the agent passes raw code from a previous step and gets back a base64 string. You don't have to manually format LangChain output code blocks anymore. The framework passes the output of your execution chain straight to this MCP Server, generating perfect images with custom window themes on the fly.

Trace Carbonara Image Generation in LangSmith

Keep an eye on every Carbonara image request by tracing the execution in LangSmith. When your chain triggers `cook_code_image`, you can inspect the exact code snippet sent and the exact size of the resulting PNG. This makes debugging Carbonara styling issues inside LangChain incredibly fast. You see the latency of the image creation and can track if your LangChain agent is feeding the correct syntax parameters to the server.

Multi-Step Code Styling in Complex Chains

Build a multi-step LangChain reasoning loop where your agent writes code, tests it, and then styles it with Carbonara. The agent uses `cook_code_image` as the final step in a sequential chain, ensuring your documentation looks clean. Because LangChain handles multi-server MCP setups, you can merge this Carbonara image generator with file-system tools. Your LangChain agent writes the code to a file and simultaneously creates a gorgeous Carbonara visual snippet for your team chat.

Setup guide

Set up Carbonara MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Carbonara tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "carbonara-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Carbonara transactions"
    })
    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 LangChain

Install the langchain-mcp-adapters package, set up the client, and pass `cook_code_image` from the MCP Server to your agent constructor. It takes less than five minutes to get running.

Yes. Your LangChain agent can specify custom styles and window controls when calling `cook_code_image` in the chain. The model decides which theme fits best based on your prompt.

It does. Every time your LangChain agent runs `cook_code_image` via MCP, the input code and output base64 string show up in your LangSmith dashboard for easy debugging.

The tool returns raw base64 data. Your Python or TypeScript code can decode this string directly into a PNG file or send it straight to a Slack webhook.

Your code snippets are processed in an ephemeral V8 sandbox. We never store your raw code or the generated PNG images on any persistent database.

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