ClaudeChatGPTPerplexityGeminiMicrosoft CopilotRaycastMeta AIGrokZ.aiQwenKimi
DeepSeekMistralCursorVS CodeWindsurfJetBrainsClineLovableVercel AI SDKLangChain

Use autoRetouch with your AI.

Connect your account once and let the AI you already use work with it, without building another integration. Retouch product photos at scale with AI-powered background removal, color correction, and beauty editing for e-commerce.

Included with plan

Ask AI about this Connector

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.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Complete set · 11 capabilities

The complete autoRetouch capability set.

These are the exact actions your AI can choose when you ask it to work with autoRetouch.

Capability set01 / 03

01-04

4 capabilities in this set.

Part of 11 available through autoRetouch.

  1. 01

    Create execution

    Returns the execution ID. Start an image processing execution

  2. 02

    Get image

    Get details of a specific image

  3. 03

    Get organization

    Get organization details

  4. 04

    Get wallet balance

    Get account wallet balance

Capability set02 / 03

05-08

4 capabilities in this set.

Part of 11 available through autoRetouch.

  1. 05

    List batches

    List all batches

  2. 06

    List images

    List uploaded images

  3. 07

    List workflows

    List all image processing workflows

  4. 08

    Get batch

    Get details of a specific batch

Capability set03 / 03

09-11

3 capabilities in this set.

Part of 11 available through autoRetouch.

  1. 09

    Get execution

    Get details of a specific execution

  2. 10

    Get workflow

    Get details of a specific workflow

  3. 11

    List executions

    List recent executions

Observed, not estimated

857ms average. Fast in production.

autoRetouch is checked daily against the live service.

Daily averagePeak 1107ms
Aug 20Today
Fastest day
710ms
Slowest day
1107ms
14-day trend
Slowing+10%

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.

Connector linkhttps://edge.vinkius.com/vk_preview_5AWw7Y7S7Xbt5L7ntz9BdW1fFNyLMk1GJi8fnC6W/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — autoRetouch capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "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

FAQ

Questions autoRetouch owners ask.

  • 01

    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.

  • 02

    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.

  • 03

    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.