How to Use the autoRetouch MCP in Mastra AI

Q: Can I run conditional autoRetouch workflows with Mastra AI?

Yes, you can branch steps based on the outputs of getworkflow or getwalletbalance. For example, you can route high-priority batches to specific workflows while flagging low-balance accounts.

Q: Can I require human approval before running a batch?

Yes, use Mastra's requireToolApproval setting on the createexecution tool. This holds the process until an operator confirms the batch size and cost fetched by getbatch.

Build resilient, self-healing photo editing pipelines with Mastra AI and autoRetouch.

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 Mastra AI

Create your Vinkius account to connect autoRetouch to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated retries for large autoRetouch batches

When processing thousands of product images, network blips happen. Mastra AI wraps calls to `create_execution` in resilient retry loops with exponential backoff. If a batch fails mid-way, the agent checks `get_batch` to find where it stopped and resumes automatically. You do not have to write custom error-handling loops for your image pipelines.

Conditional branching for MCP Server workflows

Design complex logic based on your account status. Your Mastra agent can check `get_wallet_balance` and branch its behavior based on the remaining funds. If funds are low, the workflow pauses and alerts your team instead of triggering `create_execution`. If funds are fine, it proceeds to pull your workflow list using `list_workflows`.

Human approval for expensive photo runs

Do not let agents burn your budget on massive batches without a sanity check. Set up a Mastra workflow that uses `list_images` to show pending uploads to a manager first. Once approved, the agent fires `create_execution` to start the processing. You get complete control over your spend while keeping the actual editing fully automated.

Setup guide

Set up autoRetouch MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All autoRetouch tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "autoretouch-mcp-client",
  servers: {
    "autoretouch-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "autoRetouch Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to autoRetouch tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent autoRetouch transactions"
);
console.log(result.text);

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 Mastra AI

This MCP Server integrates with Mastra's built-in queue system. If create_execution hits a rate limit, the system backs off and retries automatically without failing the entire run.

Yes, you can branch steps based on the outputs of get_workflow or get_wallet_balance. For example, you can route high-priority batches to specific workflows while flagging low-balance accounts.

Instantiating the client is straightforward. Use the Mastra MCPClient class, pass the endpoint URL, and spread the returned tools into your agent's tool configuration.

Yes, use Mastra's requireToolApproval setting on the create_execution tool. This holds the process until an operator confirms the batch size and cost fetched by get_batch.

This MCP Server uses secure transport to move image metadata directly between your backend and the API. Your actual images remain in your designated storage buckets, and only temporary processing tokens are exchanged.

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