Carbonara MCP for AI. Generate professional code visuals from any AI agent.

Q: Can I customize the syntax highlighting theme and font?

Yes! You can use the theme parameter (e.g., 'seti') and fontFamily or fontSize to match your preferred style perfectly.

Q: Is it possible to highlight specific lines of code in the image?

Absolutely. Use the selectedLines parameter to provide a comma-separated list of line numbers (e.g., '3,5,6') that you want to emphasize.

Q: Can I add window controls like the ones on macOS?

Yes, by setting windowControls to true, the generated image will include the classic close, minimize, and maximize buttons.

Claude

ChatGPT

Cursor

Gemini

Windsurf

VS Code

JetBrains

Vercel

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

Connect to your AI in seconds.

Carbonara takes raw code snippets and turns them into polished PNG images ready for docs, blogs, or social media. It handles syntax highlighting, lets you pick custom themes like 'seti', adds macOS window controls, and even lets you spotlight specific lines of interest.

Stop copy-pasting messy text; generate clean, professional visuals every time.

What your AI can do

Cook code image

This function generates a polished PNG image of a given code snippet with full styling control.

Generate code image

It takes a code snippet and outputs it as a base64 PNG image.

Apply syntax highlighting

The tool automatically detects or accepts a specific language to color-code the code accurately.

Style the container

You can choose custom themes, window styles (macOS look), and visual effects like drop shadows.

Ask an AI about this

Included with Plan

Waiting for input…

AI Agent

Carbonara: 1 Tool Available

Use the `cook_code_image` function to render any code snippet into a high-quality PNG image with advanced styling.

Make your AI actually useful.

Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.

Start using Carbonara on Vinkius

Cook Code Image

This function generates a polished PNG image of a given code snippet with full styling control.

Security and governance baked right in.

Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.

Claude AI

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL:

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.

Start a conversation

Open a new chat. The Carbonara integration is available immediately — no restart needed.

Antigravity

Configure Agent Environment

Open your Antigravity agent's workspace configuration or mcp-servers.json file.

Bind the Endpoint

Add the Vinkius endpoint URL to your agent's MCP connections list:

"mcp_servers": {
  "carbonara": {
    "serverUrl": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
  }
}

Provide your secure token in place of [YOUR_TOKEN_HERE] to ensure your agent requests are authenticated.

Execute

Start your Antigravity session. The agent will autonomously discover and utilize the Carbonara tools with full Vinkius guardrails applied.

VS Code Copilot

⚡

One-Click Install (Recommended)

In your Vinkius Dashboard, simply click the Add to VS Code button for this server. We'll automatically configure your local workspace.

Or configure manually

Open MCP Settings

Open VS Code, press Ctrl/Cmd + Shift + P, and search for GitHub Copilot: MCP Servers.

Add Server Config

Add the Vinkius endpoint configuration to your mcp-servers.json file:

"carbonara": {
  "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
}

Ensure you replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.

LangChain

Install Dependencies

Install the LangChain MCP adapters for your environment:

pip install langchain-mcp-adapters

Connect the Server

Use the SSEClient in LangChain to connect to the Vinkius managed endpoint:

from langchain_mcp_adapters.client import SSEClient

# Connect to Vinkius
client = SSEClient(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
tools = client.get_tools()

CrewAI

Define the Tool

Load the Vinkius MCP tools into your CrewAI agents:

from crewai import Agent
from mcp_crewai import MCPTool

# Connect securely to Vinkius
vinkius_tools = MCPTool(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

# Assign to Agent
researcher = Agent(
    role='Data Researcher',
    tools=vinkius_tools.get_all()
)

Execute Task

Run your CrewAI process. The agent will autonomously route tasks to the Vinkius managed server.

Choose How to Get Started

Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.

Build Your Own

Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.

Import from OpenAPI, Swagger, or YAML specs
Create Agent Skills with progressive disclosure
Deploy to edge with MCPFusion framework
Built in DLP, auth, and compliance on every call
Real time usage dashboard and cost metering
Publish to catalog or keep private

Start building

Make Your AI Do More

Start with Carbonara, then connect any of our 5,100+ other servers whenever your AI needs more. One click, no limits.

Use this MCP plus 5,100+ others, all in one place
Add new capabilities to your AI anytime you want
Every connection is secured and compliant automatically
Track usage and costs across all your servers
Works with Claude, ChatGPT, Cursor, and more
New servers added to the catalog every week

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.

VINKIUS INFRASTRUCTURE

Cloud Hosted

Managed infra

V8 Isolated

Sandboxed per request

Zero-Trust Proxy

No stored credentials

DLP Enforced

Policy on every call

GDPR Compliant

EU data residency

Token Compression

~60% cost reduction

Your data is protected. See how we built it.

Works with Claude, ChatGPT, Cursor, and more

The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.

This connection provides 1 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.

Today, showing code in documentation means endless copy-pasting and formatting headaches.

Right now, if you write an API guide or a tutorial, the process is manual hell. You pull a snippet from your IDE, paste it into Notion or Confluence, then you spend ten minutes adjusting the font size, picking a background color, and trying to make sure the syntax highlighting didn't break. It’s tedious, time-consuming, and consistency is a pipe dream.

With this MCP, that whole process vanishes. You just hand your agent the code block and tell it what you want—say, 'Use the seti theme.' The agent calls `cook_code_image`, and boom. You get a perfect PNG image, instantly styled and ready to drop into your final document.

Carbonara MCP provides visually consistent code documentation.

You eliminate the need for multiple styling passes. No more toggling between 'GitHub style' and 'VS Code style.' You tell your agent what you want, whether it's adding macOS window controls or a custom background color, and the tool handles the rendering details.

It’s about consistency. Every code snippet across your entire platform will look like it came from the same source, making your documentation feel professional and cohesive.

Support 24/7 support@vinkius.com ↗

Security Vinkius Trust Center ↗

SLA Service Level Agreement ↗

Report Listing Send Report ↗

What your AI can actually do with this

Writing technical documentation means dealing with code constantly. You need snippets that look good, not just blocks of text. This MCP connects your AI agent to a visual engine designed for exactly that. It lets you render any language—from Python to SQL—into beautiful, high-resolution images. You control the style: choose between sharp or rounded window aesthetics, add drop shadows, and even toggle line numbers on or off.

Instead of manually styling code in an editor just to take a screenshot, your agent handles the heavy lifting. Whether you're writing tutorials or updating internal runbooks, this lets you generate consistent visuals with minimal effort. If you need one place to connect all your visual tools, Vinkius hosts and manages Carbonara right alongside hundreds of other specialized MCPs.

Built · Hosted · Managed by Vinkius Carbonara MCP - Generate Styled Code Screenshots

Server ID 019e5d05-3739-7282-ab22-c0cb0e6c6f48

Vinkius Inspector

Compliance Grade A+

Score 100/100

Report View Report ↗

What Changes When You Connect

Consistency is guaranteed. You get the same look and feel—from window controls to syntax highlighting—every time you use cook_code_image.

Stop dealing with messy screenshots. This MCP handles advanced formatting, letting you toggle line numbers or highlight specific lines of interest directly in the prompt.

It supports multiple languages and themes (like 'seti'). You just tell your agent what language it is, and the tool does the rest.

The resulting PNG image includes professional window styling (macOS-style controls), making documentation look polished and finished.

You don't need to open a separate design program. Your AI client handles the entire rendering process through this MCP.

See it in action

01 01

Writing an API reference guide

A technical writer needs to show five different Python functions in the documentation. Instead of manually capturing and editing each one, they ask their agent to cook_code_image for all five with a consistent theme and window style. They end up with five perfectly styled visuals ready for publishing.

02 02

Sharing a complex React component

A developer needs to show their team how a new UI component works in a chat message. They prompt the agent, asking it to render the code using a blue background and drop shadow. The result is a visually rich image, not just plain text.

03 03

Creating a teaching slide deck

An instructor needs clear visual aids for an SQL query tutorial. They ask their agent to generate the image using cook_code_image, specifically requesting that lines 2 and 4 be highlighted. The resulting image immediately draws attention to the key concepts.

The honest tradeoffs

Simple copy-pasting

Anti-pattern

Copying code from an IDE or browser into a document editor results in messy, inconsistent formatting that looks amateur.

The Fix

Use the cook_code_image tool. Your agent handles all the styling—themes, window controls, and highlighting—so you get a clean PNG image every time.

Using generic screenshot tools

Anti-pattern

Taking a standard OS screenshot captures everything around the code (toolbars, menus) and often includes jagged edges.

The Fix

The Carbonara MCP renders just the snippet. You control if it has window styling or background colors, guaranteeing a clean cutout.

Trying to format raw Markdown

Anti-pattern

Writing complex markdown blocks that rely on syntax highlighting often breaks when pasted into non-Markdown environments.

The Fix

The cook_code_image tool bypasses text formatting issues entirely. It generates a ready-to-use visual asset.

When It Fits, When It Doesn't

Use Carbonara if the final output MUST be a polished, styled image suitable for public documentation or presentation slides. For instance, when you need to show code in a blog post or teach it to someone, this MCP is necessary. Don't use it if all you need is plain text for further processing; just letting your agent print the raw snippet is faster. If your goal is merely storage of source code, don't bother—just save the file directly. Remember: cook_code_image turns a textual concept into a finished graphic artifact.

Questions you might have

Can I customize the syntax highlighting theme and font? +

Yes! You can use the theme parameter (e.g., 'seti') and fontFamily or fontSize to match your preferred style perfectly.

Is it possible to highlight specific lines of code in the image? +

Absolutely. Use the selectedLines parameter to provide a comma-separated list of line numbers (e.g., '3,5,6') that you want to emphasize.

Can I add window controls like the ones on macOS? +

Yes, by setting windowControls to true, the generated image will include the classic close, minimize, and maximize buttons.

What languages can I use when calling cook_code_image? +

Yes, it supports a wide variety of popular programming languages. When you make your request to cook_code_image, simply specify the language in your prompt for accurate syntax highlighting.

How does the cook_code_image tool deliver its output? +

The tool returns the result as a base64 encoded PNG string. Your AI client can then decode this data directly to display the image in your chat interface or application.

What is the best way to set up Carbonara for cook_code_image? +

You must provide a valid, accessible Base URL for your Carbonara instance. You'll find instructions on setting up this endpoint in the Vinkius Marketplace configuration panel.

Can I control custom background colors or shadows with cook_code_image? +

Yes. The tool allows you to pass parameters that define visual effects, such as customizing background colors and adding soft drop shadows for a polished look.

Are there rate limits if I generate many images using cook_code_image? +

Since this is an external API service, you should check your hosting provider's documentation. If generating dozens of images, be sure to implement appropriate retry logic for rate limiting.

Connect to your AI in seconds.

Cook code image

Carbonara: 1 Tool Available

Make your AI actually useful.

Cook Code Image

Security and governance baked right in.

Claude AI

Open Claude Settings

Add Custom Connector

Start a conversation

Claude Code

Open your terminal

Add the MCP Server

Start coding

Cursor

One-Click Install (Recommended)

Open Cursor Settings

Add New Server

Use in Composer

Antigravity

Configure Agent Environment

Bind the Endpoint

Execute

VS Code Copilot

One-Click Install (Recommended)

Open MCP Settings

Add Server Config

Windsurf

One-Click Install (Recommended)

Open Windsurf Settings

Add Server Endpoint

LangChain

Install Dependencies

Connect the Server

CrewAI

Define the Tool

Execute Task

Choose How to Get Started

Build Your Own

Make Your AI Do More

Works with Claude, ChatGPT, Cursor, and more

Today, showing code in documentation means endless copy-pasting and formatting headaches.

Carbonara MCP provides visually consistent code documentation.

What your AI can actually do with this

Here's how it actually works

Who is this actually for?

What Changes When You Connect

See it in action

Writing an API reference guide

Sharing a complex React component

Creating a teaching slide deck

The honest tradeoffs

Simple copy-pasting

Using generic screenshot tools

Trying to format raw Markdown

When It Fits, When It Doesn't

Questions you might have