How to Use the autoRetouch MCP in Vercel AI SDK

Q: How do I handle autoRetouch billing checks in Vercel AI SDK?

Your agent can call getwalletbalance to check funds before starting an edit. The SDK streams this balance directly to your pricing or checkout component. It prevents failed API calls due to empty wallets.

Pipe real-time product photo edits directly into your Next.js UI using the Vercel AI SDK.

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 Vercel AI SDK

Create your Vinkius account to connect autoRetouch to Vercel AI SDK 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 Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live-stream photo workflows to your UI

Your users do not want to stare at a spinner while wait times tick up. Feed the `create_execution` tool directly to your frontend using Vercel AI SDK's edge-compatible stream. They will watch the autoRetouch pipeline execute step-by-step in real-time. By calling `list_workflows` inside your streaming text component, your agent can instantly show available templates to the user. No lag. They choose a workflow, and the SDK spins up the execution instantly.

Real-time wallet and batch monitoring

Keep users informed about their usage costs without forcing page reloads. This MCP Server lets your agent fetch current credits with `get_wallet_balance` and push that status straight to a React component. If a user launches a massive catalog update, the Vercel AI SDK streams live progress from `get_batch`. They see exactly how many product shots are finished and how much budget remains.

Instant image previews in Vercel AI SDK

Show users their processed assets the millisecond they are ready. Your agent runs `get_image` to pull processed variants and streams the URLs directly into your UI layout. This setup bypasses slow backend polling by letting the client handle the state. You get a fast, responsive interface that displays finished catalog images without refreshing.

Setup guide

Set up autoRetouch MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all autoRetouch tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent autoRetouch transactions",
});

console.log(text);
await mcpClient.close();

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 Vercel AI SDK

Use streamText and pass the tools from your MCP client. When the agent calls get_execution, the SDK streams the status updates straight to your React hooks. This prevents UI blocking during heavy image rendering.

Yes, this MCP Server works perfectly on Vercel Edge Functions. You initialize the client, fetch workflow details with get_workflow, and close the connection when done. It keeps your serverless execution times low and fast.

Your agent can call get_wallet_balance to check funds before starting an edit. The SDK streams this balance directly to your pricing or checkout component. It prevents failed API calls due to empty wallets.

Always call mcpClient.close() when your execution finishes. This is critical in serverless environments to prevent hanging sockets. It keeps your Vercel functions lean and efficient.

Your product images are processed in a highly secure, ephemeral sandbox. This MCP Server only passes image metadata and temporary URLs to the Vercel AI SDK. Your raw master files are never stored permanently or used for model 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