How to Use the autoRetouch MCP in Google ADK

Q: Can I restrict which image tools my Gemini agent can access?

Yes, you can use the optional toolnames filter in McpToolset. This lets you restrict your agent to read-only tools like listimages and getimage if you want to prevent it from starting new paid runs.

Process enterprise catalog photos at scale by connecting autoRetouch to Google ADK and Gemini.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect autoRetouch MCP to Google ADK

Create your Vinkius account to connect autoRetouch 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 autoRetouch with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Scale e-commerce editing with Google ADK

Connect your raw BigQuery inventory tables directly to your photo editing pipeline. Your Gemini agent reads product SKUs from your database and uses `create_execution` to kick off background removal for thousands of new arrivals. It handles the scale without breaking a sweat, thanks to the massive context window. The agent monitors the progress by calling `list_executions` and mapping the results back to your cloud database. This removes the manual step of downloading, editing, and re-uploading catalog photos.

Let Gemini choose the right MCP Server workflow

Different products need different editing styles. Your agent calls `list_workflows` to find the correct template, whether it is a ghost mannequin setup for apparel or a shadow-drop for footwear. It reads the product category from Vertex AI and matches it to the right edit. Once it finds a match, it uses `get_workflow` to verify the specifications before running the batch. This ensures your jewelry shots do not accidentally get the apparel editing treatment.

Manage multi-brand assets in Google Cloud

For large enterprise setups, tracking who processed what is critical. The agent uses `get_organization` and `get_wallet_balance` to monitor usage across different brand departments. It attributes costs accurately without requiring manual spreadsheet tracking. It keeps your asset library clean by calling `list_images` and matching them to your Google Cloud Storage buckets. Your agent can clean up old temporary files once `get_batch` confirms that the processed assets are safely stored in your production database.

Setup guide

Set up autoRetouch 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 autoRetouch 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="autoRetouch_agent",
    model="gemini-2.0-flash",
    instruction="You have access to autoRetouch 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 autoRetouch. 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 autoRetouch 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 autoRetouch MCP in Google ADK

Install the SDK via pip, then wrap the server URL in McpToolset using StreamableHttpServerParameters. Pass this toolset directly into the tools list of your LlmAgent to let Gemini discover the image tools.

Yes, your Gemini agent can read product listings from BigQuery, identify which items lack polished photos, and call create_execution to start editing. It bridges your enterprise data directly to your creative assets.

The MCP Server is built for bulk operations. Your agent can group hundreds of images into a single batch using list_batches, allowing Gemini to monitor high-volume e-commerce pipelines without hitting rate limits.

Yes, you can use the optional tool_names filter in McpToolset. This lets you restrict your agent to read-only tools like list_images and get_image if you want to prevent it from starting new paid runs.

Your product photos are processed using secure HTTPS connections. The image metadata and temporary links accessed by the agent are isolated within your Google Cloud environment, ensuring no third-party exposure of your unreleased catalog.

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