How to Use the Carbonara MCP in Google ADK

Q: How do I load Carbonara into the Google ADK?

Create an McpToolset using StreamableHttpServerParameters and your Vinkius URL. Then pass it to the LlmAgent under the tools array.

Render syntax-highlighted code images from massive Gemini contexts using the Google ADK.

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 Google ADK

Create your Vinkius account to connect Carbonara to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Massive Context Rendering via MCP Server

Generating beautiful syntax-highlighted code images from massive codebases requires serious context. Gemini models hold over a million tokens, meaning they can analyze entire repositories at once to find the exact function you need. Invoking `cook_code_image` turns that specific block into a base64 PNG. You get a styled graphic with window controls, ready for your documentation site or internal wiki.

Native Google Cloud Workflows

Enterprise teams already store their logic and logs in BigQuery. Your Google ADK agent queries that data, finds the relevant snippets, and prepares them for visualization. The MCP Server pipeline moves the extracted logic straight into the renderer. It spits back a clean image without you ever leaving the Vertex AI environment.

Filtered Tool Execution

Exposing too many actions confuses even smart models. You restrict the agent by applying a `tool_names` filter when setting up the connection. The system only sees the image generation capability. This focused approach stops the model from hallucinating other commands and guarantees it sticks to creating visual code blocks.

Setup guide

Set up Carbonara MCP in Google ADK

Prerequisites

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

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Carbonara tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Carbonara_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Carbonara tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Create an `McpToolset` using `StreamableHttpServerParameters` and your Vinkius URL. Then pass it to the `LlmAgent` under the `tools` array.

The Gemini context window handles the massive file reading. The agent isolates the specific function and sends just that snippet to the MCP tool for rendering.

You configure the toolset to use HTTP transport specifically for this integration. Stdio is available, but the Vinkius endpoint requires the HTTP route.

You receive a base64 encoded PNG string. Your application logic takes that string and writes it to a standard image file on your storage bucket.

The renderer operates inside a zero-trust sandbox that wipes itself clean after every request. The code snippets you pull from your data warehouse vanish the millisecond the PNG generates.

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