How to Use the Unsplash Extended MCP in Vercel AI SDK

Q: How do I use Unsplash Extended with Vercel AI SDK?

You call the unsplash-extended-mcp client through your Edge Function. The result streams back to your React component, letting you display photos found via getphoto immediately.

Q: What is the best way to search photos with Unsplash Extended and Vercel AI SDK?

Just use searchphotos. Because of streaming support in Vercel AI SDK, you'll see results populate instantly as they come from the server. It’s much faster than waiting for a full response.

Q: Can Unsplash Extended handle user actions with Vercel AI SDK?

Yes. You can use likephoto or unlikephoto. The result streams back, confirming the action to your client in real time, which is crucial for a smooth UX.

Q: How do I check user stats using Unsplash Extended and Vercel AI SDK?

Call getuserstatistics. The data flows through the streaming MCP Server connection. This ensures your UI gets the view count or download metric without delay.

Display real-time photo data in your UI with 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 Unsplash Extended MCP to Vercel AI SDK

Create your Vinkius account to connect Unsplash Extended 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 Unsplash Extended with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-Time MCP Server Integration

The `unsplash-extended-mcp` tool streams results directly into the client UI. You can call `get_photo` or `search_photos`, and the data appears instantly, letting your users see the AI working live without a loading spinner. Edge Functions handle this well. Developers use this to build user-facing products where photo search results stream in real time, making the experience feel immediate.

Managing Photo Collections

Need users to manage images? Use `create_collection` and `add_photo_to_collection`. Your agent client can execute these calls, allowing you to build frontends where user-created collections are visible as they are built. When a collection changes, the data streams out. This means you get immediate feedback when calling `update_collection` or running `remove_photo_from_collection`.

Listing and Searching Content

`unsplash-extended-mcp` gives you access to photo listings, topics, and users. You can stream the output of `list_topics`, or run targeted searches using `search_photos`. This makes displaying a curated feed look natural. The streaming capability is huge here. Instead of waiting for 50 photos to load at once, your UI gets chunks of data as soon as they're ready.

Setup guide

Set up Unsplash Extended 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 Unsplash Extended 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 Unsplash Extended 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 Unsplash. 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 Unsplash Extended 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 Unsplash Extended MCP in Vercel AI SDK

You call the `unsplash-extended-mcp` client through your Edge Function. The result streams back to your React component, letting you display photos found via `get_photo` immediately.

Just use `search_photos`. Because of streaming support in Vercel AI SDK, you'll see results populate instantly as they come from the server. It’s much faster than waiting for a full response.

Yes. You can use `like_photo` or `unlike_photo`. The result streams back, confirming the action to your client in real time, which is crucial for a smooth UX.

Call `get_user_statistics`. The data flows through the streaming MCP Server connection. This ensures your UI gets the view count or download metric without delay.

This server touches User Profile and Photo Metadata. The client needs to handle this sensitive data flow via the streaming API, so make sure your authProvider is locked down.

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