How to Use the NiftyImages MCP in Vercel AI SDK

Q: How does NiftyImages handle live streaming updates in Vercel AI SDK?

The server uses updatepsdimage to modify layers and immediately streams the updated asset metadata. Your Vercel AI SDK application captures this stream to update the dynamic image preview in real-time.

Q: Can I display NiftyImages datastore fields inside a Vercel AI SDK UI?

Yes. The agent calls listdatastorefields to inspect your custom data schemas and immediately streams the field names into your React forms.

Q: How do I track NiftyImages click metrics using Vercel AI SDK?

Your agent runs getimagestats to pull real-time open and click counts. The Vercel AI SDK then streams these metrics directly into your live dashboard components.

Stream personalized email graphics directly into your React views using NiftyImages with 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 NiftyImages MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Live performance metrics in React

The `get_image_stats` tool pulls raw email engagement metrics directly into your Vercel AI SDK stream. Your UI renders these open rates and click counts live as they stream from the server, skipping the standard loading state entirely. Your agent uses `get_widget_stats` to compare dynamic widget performance side-by-side in your dashboard. Because this runs on edge-compatible endpoints, you get instant rendering without blocking the main browser thread.

Updating PSD templates via Vercel AI SDK

The `update_psd_image` tool modifies Photoshop layers dynamically inside your Vercel AI SDK chat interface. When your user requests a text change on a promotional banner, the agent triggers the update and immediately streams the new image URL. We use this MCP Server to feed the updated asset variables directly into your React component state. This means your marketing team sees the updated layout render on their screen without a manual page refresh.

Direct countdown timer control

The `update_timer` tool modifies dynamic email countdown deadlines directly through your streaming agent interface. If a flash sale gets extended, your agent updates the countdown end-time on the fly. The Vercel AI SDK receives the confirmation payload from the MCP and instantly updates the preview component on your Next.js frontend. No background cron jobs or manual API client configurations are required to synchronize the timer.

Setup guide

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

The server uses `update_psd_image` to modify layers and immediately streams the updated asset metadata. Your Vercel AI SDK application captures this stream to update the dynamic image preview in real-time.

Yes. The agent calls `list_datastore_fields` to inspect your custom data schemas and immediately streams the field names into your React forms.

Your agent runs `get_image_stats` to pull real-time open and click counts. The Vercel AI SDK then streams these metrics directly into your live dashboard components.

No. The Vinkius platform handles the underlying transport, leaving you to just pass the MCP Server tools directly into `streamText`.

Every request containing your subscriber datastore records runs inside an isolated V8 sandbox on Vinkius. Your API keys are encrypted at rest and never exposed to the LLM or client-side code.

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