How to Use the DeepAI MCP in Vercel AI SDK

Q: How do I authenticate the DeepAI MCP Server in Vercel AI SDK?

You pass your Vinkius endpoint token directly into the createMCPClient constructor. For user-specific operations, configure the authProvider option to handle OAuth tokens dynamically during the stream.

Q: Can I stream DeepAI image edits directly to a React frontend with Vercel AI SDK?

Yes. By passing the tools from mcpClient.tools() to streamText, the generated image URLs from editimage render live in your UI components. This removes the need for polling or manual state management.

Q: How do I handle multiple image edits in a single session?

Pass both editimage and superresolution to your agent. The model decides when to modify the image and when to upscale it based on the user's natural language requests.

Render live DeepAI image generation and edits directly inside your React components using 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 DeepAI MCP to Vercel AI SDK

Create your Vinkius account to connect DeepAI 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 DeepAI with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time image generation in Vercel AI SDK

The `generate_image` tool creates high-resolution visual assets from plain text prompts directly inside your streaming UI. Your users watch the pixels resolve as the server processes the request, bypassing those annoying static loading spinners. We built this to work with the `@ai-sdk/mcp` client. Call `mcpClient.tools()` and pass them to `streamText` to pipe the raw generated image URLs right into your Next.js edge functions.

On-the-fly background removal

The `remove_background` tool isolates subjects by stripping out background noise from any uploaded image. This tool handles the heavy lifting on the DeepAI servers, returning clean PNG assets directly to your application state. You feed the image URL to your agent, which calls the tool and updates the UI instantly. Our hosted MCP server runs on our zero-trust V8 sandbox, keeping your user's source files isolated and secure.

Instant resolution upscaling and colorization

The `super_resolution` and `colorize_image` tools restore historical or low-quality photos by adding realistic color and sharpening blurry details. These tools process raw image inputs and output clean, high-fidelity URLs that render immediately in the browser. Your TypeScript code coordinates these actions in a single execution block. Just remember to call `mcpClient.close()` once the upscaling completes to keep your edge function execution times tight.

Setup guide

Set up DeepAI 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 DeepAI 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 DeepAI 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 DeepAI. 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 DeepAI 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 DeepAI MCP in Vercel AI SDK

You pass your Vinkius endpoint token directly into the `createMCPClient` constructor. For user-specific operations, configure the `authProvider` option to handle OAuth tokens dynamically during the stream.

Yes. By passing the tools from `mcpClient.tools()` to `streamText`, the generated image URLs from `edit_image` render live in your UI components. This removes the need for polling or manual state management.

No. The MCP server runs on Vinkius's managed infrastructure, keeping your Vercel edge functions lightweight. You get fast HTTP responses without hitting local CPU or memory limits.

Pass both `edit_image` and `super_resolution` to your agent. The model decides when to modify the image and when to upscale it based on the user's natural language requests.

Your raw images process inside ephemeral V8 isolates that destroy themselves immediately after execution. We never store your image files on persistent disks, and all traffic travels over encrypted TLS channels.

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