
Connect autoRetouch to ChatGPT, Claude and Gemini
Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Process high-volume product photos without leaving your AI workspace.
Developed, maintained, and hosted by Vinkius.
MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED
Waiting for input…
Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.
Your AI does the work. We keep it safe and sound.
No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.
Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

Each Connector runs inside its own sealed environment.
Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.
One switch stops every agent. Instantly.
One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.
Spending limits that pause instead of surprise.
Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.
Three controls, built into the layer your AI connects through.
Curated set · 11 capabilities
We ship only the actions that matter.
01-04
4 capabilities in this set.
Part of 11 available through autoRetouch.
- 01
Create execution
Starts a new image processing job and returns the unique execution ID for tracking.
- 02
Get image
Retrieves specific details about a single image asset you've uploaded.
- 03
Get organization
Pulls core details about your organization's account setup.
- 04
Get wallet balance
Checks your current account wallet balance for instant financial reporting.
05-08
4 capabilities in this set.
Part of 11 available through autoRetouch.
- 05
List batches
Lists all the batch jobs you've set up for processing.
- 06
List images
Shows a list of all raw images you've uploaded to the system.
- 07
List workflows
Retrieves a list of all available image processing workflows you've configured.
- 08
Get batch
Gets detailed information about a specific batch job.
09-11
3 capabilities in this set.
Part of 11 available through autoRetouch.
- 09
Get execution
Retrieves the status and details for a specific, running image processing job.
- 10
Get workflow
Fetches the specific details of a workflow template.
- 11
List executions
Lists recent image processing jobs so you can check on past activity.
Real work
What teams actually run
Catalog Refresh
You have 500 new products. Instead of processing them one by one, you ask the MCP to run the 'Bulk Background Remove' workflow on the entire batch.
Campaign Asset Prep
A client needs 20 images color-corrected and given a consistent shadow effect. You run the 'Shadow Gen' workflow across the group.
Audit and QA
You need to verify which images were processed last week and check the final result URL for a specific job ID.
Billing Check
Before starting a massive job, you check your wallet balance to ensure you have enough credits for the entire batch.
Automate a task
Put autoRetouch to work on one thing.
Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.
One connector, every AI
autoRetouch works with the most popular AI clients.
These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.
Claude
ChatGPT
Gemini
Perplexity
Grok
Microsoft Copilot
Cursor
VS Code
Windsurf
JetBrains
Cline
LangChain
Vercel AI SDK
Lovable
Z.ai
Raycast
Qwen Code
Kimi Code
Le ChatBuilding your own app? The connector is yours to use.
You don't need a client to put autoRetouch to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.
Observed, not estimated
950ms average. Fast in production.
autoRetouch is checked daily against the live service.
- Fastest day
- 735ms
- Slowest day
- 1236ms
- 14-day trend
- Slowing+40%
Connect your client
One URL. Every client.
Activate the Connector, copy your link, and paste it into the client you already use. 11 capabilities arrive ready to run.
Preview access · not provider authentication
The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of autoRetouch, so you can see the experience inside your AI.
It does not authenticate your account with autoRetouch. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.
autoRetouch Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_5AWw7Y7S7Xbt5L7ntz9BdW1fFNyLMk1GJi8fnC6W/mcpClaude Desktop
Follow the steps below to connect in seconds.
- 1In Claude Desktop, open Settings → Connectors.
- 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
- 3Click Add and start a new chat — autoRetouch capabilities are ready to use.
{
"mcpServers": {
"autoretouch-mcp": {
"url": "https://edge.vinkius.com/vk_preview_5AWw7Y7S7Xbt5L7ntz9BdW1fFNyLMk1GJi8fnC6W/mcp"
}
}
}
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Step-by-step instructions for each client are in the guide. How to connect
Guided setup for Claude? Set up autoRetouch in Claude and other AIs
Who it's for
Built for the work autoRetouch owners hand off.
This MCP is built for professionals who deal with high volumes of product photography. If you spend time manually cleaning up, resizing, or adjusting product images for an online store, this capability saves you hours. It lets you manage entire media pipelines from a single conversation.
- 01
E-commerce Merchants
Process massive product photo updates for catalog refreshes using simple natural language commands.
- 02
Marketing Agencies
Automate background removal and color balancing for client campaigns without leaving your creative workspace.
- 03
Photographers
Orchestrate complex retouching sequences across large batches of images through simple AI queries.
FAQ
Questions autoRetouch owners ask.
- 01
Does this MCP handle multiple types of retouching?
Yes. It supports multiple high-fidelity AI workflows, including background removal, color correction, and shadow generation. You can select the specific workflow needed for your assets.
- 02
Can I process images in bulk?
Absolutely. You can programmatically upload raw images and group multiple executions into tracked batches. This lets you oversee large volumes of image editing efficiently.
- 03
How do I check if a job finished?
You can use the MCP to get the details of a specific execution. This tells you the current status, and if successful, provides the direct result URL for the processed image.
- 04
Do I need to use a specific AI model?
No. You connect this MCP using any MCP-compatible client, including Claude, Cursor, or Windsurf. The connector handles the communication regardless of your underlying AI model.
- 05
What kind of data can I access about my account?
You can access your organization's profile metadata, view your current wallet balance, and list all past batches and workflows.
- 06
How do I find my autoRetouch API credentials?
Log in to your account, navigate to the API section to generate an Access Token (Bearer), and find your Organization ID in the organization settings.
- 07
Can I process multiple images at once?
Yes! You can trigger individual executions programmatically and group them into a single batch for high-fidelity tracking.
- 08
What happens if a process fails?
The get_execution_status capability will return high-fidelity error metadata to help you diagnose and re-run the task programmatically.
Explore
More in Ecommerce
Remove.bg AI Connector
Remove image backgrounds automatically in seconds using AI — process URLs or base64 images and manage your cre
ViewClaid AI AI Connector
Automate AI image processing via Claid — upscale resolution, remove backgrounds, and enhance product photos di
ViewPhotoroom AI Connector
Remove backgrounds, retouch product photos, and generate studio-quality images with AI editing tools built for
ViewDeepAI AI Connector
Generate and edit images using AI — create art from text, remove backgrounds, colorize photos, and upscale ima
View
Suggestions
Viesus AI Connector
Enhance photos automatically with AI that adjusts exposure, color balance, and sharpness to make every image l
ViewPhotography Series Editing Plan AI Connector
A strategic engine to transform raw photographic assets into structured editorial roadmaps.
Viewimgix (Real-time Image Processing) AI Connector
Optimize and transform images via imgix — manage CDN sources, purge assets, and monitor origin connections.
ViewAPImage AI Connector
Search and license editorial photography from one of the world largest press image archives for media and publ
View
Connect autoRetouch to Claude, Cursor, ChatGPT & more
