How to Use the Unsplash MCP in Vercel AI SDK

Q: How do I search for photos using Unsplash and Vercel AI SDK?

You use the searchphotos tool. This function lets you input keywords to get photo IDs, URLs, and attribution info immediately. The result streams directly into your frontend component as soon as it's processed by the MCP Server.

Q: Can I find curated topics with Unsplash and Vercel AI SDK?

Yep. Just run listeditorialtopics. This lists categories like 'Nature' or 'Industrial,' letting you build a filter for your users. The data streams, so your UI updates without delay.

Q: What kind of photos can I retrieve with Unsplash and Vercel AI SDK?

You can get random high-res images using getrandomphoto. You can even pass a query to narrow that selection. The result is streamed, so the user sees the image URL pop into place in real time.

Q: What if I need to find a specific photographer using Unsplash and Vercel AI SDK?

Use searchphotographers. You pass in a name or username, and the MCP Server returns matching profiles. This helps you build out author pages for your application.

Get real-time photo data streaming into your frontend 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 Unsplash MCP to Vercel AI SDK

Create your Vinkius account to connect Unsplash 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 with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Displaying Unsplash results with the Vercel AI SDK

When you call `mcpClient.tools()` and stream the results, users see photo data appearing live in their UI. You can instantly show a user the details of a specific image using `get_photo_details` as soon as it's retrieved. This streaming capability means no loading spinner delay. The moment your agent gets photo metadata or collection information from this MCP Server, you display it immediately.

Search results for Vercel AI SDK

Need inspiration fast? Use `search_photos` to return IDs and URLs directly into your client component. This works great in Edge Functions because the data streams out quickly. Alternatively, you can use `list_editorial_topics` to populate a dynamic dropdown filter before running a targeted search for collections.

Building photo galleries with Vercel AI SDK

To build a whole gallery view, start by calling `search_collections`. This function returns names like 'Nature' or 'Architecture,' which you can then use to populate a collection ID. From that ID, you call `list_collection_photos`. The results stream right into your React component. Your user never waits for a bulk API response; they see the photo list appear as the data arrives.

Setup guide

Set up Unsplash 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 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 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 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 MCP in Vercel AI SDK

You use the `search_photos` tool. This function lets you input keywords to get photo IDs, URLs, and attribution info immediately. The result streams directly into your frontend component as soon as it's processed by the MCP Server.

Yep. Just run `list_editorial_topics`. This lists categories like 'Nature' or 'Industrial,' letting you build a filter for your users. The data streams, so your UI updates without delay.

You can get random high-res images using `get_random_photo`. You can even pass a query to narrow that selection. The result is streamed, so the user sees the image URL pop into place in real time.

The server touches public-facing photo IDs, URLs, and photographer names. It does not touch private user account or payment information, so the risk is low.

Use `search_photographers`. You pass in a name or username, and the MCP Server returns matching profiles. This helps you build out author pages for your application.

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