How to Use the Leonardo.ai (Generative AI & Models) MCP in Google ADK

Q: Can Google ADK agents manage custom trained models on Leonardo.ai (Generative AI & Models)?

Yes. The agent can run listcustommodels to fetch your team's fine-tuned models, allowing Gemini to select the perfect style guide for generating brand-compliant assets.

Q: How does Google ADK handle image uploads for Leonardo.ai (Generative AI & Models) workflows?

The agent calls uploadinitimage to get a secure upload target, uploads the file from Google Cloud Storage, and references it in subsequent image-to-image generations.

Connect Leonardo.ai (Generative AI & Models) to Google ADK to build visual pipeline agents backed by Gemini and BigQuery.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Leonardo.ai (Generative AI & Models) MCP to Google ADK

Create your Vinkius account to connect Leonardo.ai (Generative AI & Models) 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 Leonardo.ai (Generative AI & Models) with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed BigQuery insights into Leonardo.ai via Google ADK

Your Gemini-backed Google ADK agents can query structured marketing data in BigQuery and immediately convert those insights into Leonardo.ai visual prompts. The agent triggers `generate_image` using the exact parameters retrieved from your database tables. By using this MCP Server, your enterprise pipeline connects Google Cloud data directly to Leonardo.ai image generation without custom API glue code.

Contextual image expansion with Gemini reasoning

Use Gemini's deep reasoning within Google ADK to analyze existing visual assets and decide how to extend them. The agent calls `create_variation` to unzoom and expand the context of a Leonardo.ai image based on the surrounding design files. This MCP Server integration lets your Google ADK agent handle complex Leonardo.ai canvas modifications programmatically, matching the aesthetic of your original generation.

Audit model performance across your enterprise team

Track Leonardo.ai model usage and track metrics across large teams using Google ADK. Your agent pulls active user data using `get_user` and combines it with `list_platform_models` to map which base models drive your production pipelines. This gives your Google ADK operations team clear visibility into Leonardo.ai asset generation patterns, helping you optimize costs and model selection across Google Cloud.

Setup guide

Set up Leonardo.ai (Generative AI & Models) 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 Leonardo.ai (Generative AI & Models) 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="Leonardo.ai (Generative AI & Models)_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Leonardo.ai (Generative AI & Models) 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 Leonardo.ai. 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 Leonardo.ai (Generative AI & Models) 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 Leonardo.ai (Generative AI & Models) MCP in Google ADK

Instantiate the MCP toolset with your Vinkius HTTP URL and pass it to your agent constructor. The Gemini model automatically discovers tools like `generate_image` and knows when to run them.

Yes. The agent can run `list_custom_models` to fetch your team's fine-tuned models, allowing Gemini to select the perfect style guide for generating brand-compliant assets.

The agent calls `upload_init_image` to get a secure upload target, uploads the file from Google Cloud Storage, and references it in subsequent image-to-image generations.

You can pass a filtered list of tool names to the toolset constructor, blocking destructive actions like `delete_generation` while keeping generation tools active.

Yes. All prompt text and generation histories are processed within an isolated V8 sandbox that wipes transient data instantly. No information is stored on Vinkius servers or used for public training.

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