How to Use the Getty Images MCP in Vercel AI SDK

Q: How do I connect Getty Images to my Vercel AI SDK project?

Install @ai-sdk/mcp and call createMCPClient with your HTTP endpoint URL. Pass the tools array directly into streamText to let your agent query assets.

Q: Can Vercel AI SDK stream Getty Images video metadata in real-time?

Yes. The agent uses searchvideos and getvideo to fetch video details, streaming the preview URLs directly into your React components without delay.

Q: How do I prevent my Vercel AI SDK agent from overspending our Getty Images quota?

Configure your agent to only call searchimages and getimage for previews. Restrict access to downloadimage by wrapping it in a custom tool approval step on your MCP server.

Stream live Getty Images assets directly into your Next.js UI using Vercel AI SDK without waiting for slow API loading states.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Getty Images MCP to Vercel AI SDK

Create your Vinkius account to connect Getty Images 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 Getty Images with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream live media search results via Vercel AI SDK

`search_images` queries your target keywords and instantly sends raw image metadata to your front-end components. Instead of forcing users to stare at a loading spinner, your application renders preview URLs and captions as they arrive from the Getty API. By calling `get_images_batch`, your application pulls multiple asset records in a single round-trip. This keeps your Edge Functions fast and prevents your database from getting slammed with redundant requests.

Protect commercial compliance with dual search tools

`search_creative` separates commercial-safe assets from editorial content to prevent costly licensing mistakes. Your agent handles this filter automatically at the schema level, routing commercial work away from restricted files. If your user needs news coverage, the agent switches to `search_editorial` instead. This ensures your production team never accidentally prints an editorial-only asset on a commercial product.

Control download costs using an MCP Server preview gate

`download_image` triggers a high-resolution file pull that directly consumes your corporate API quota limits. Because of this cost, you need to gate downloads by serving low-res preview strings first. Your agent uses `get_similar` to show users cheaper alternatives before committing to a download. This MCP server setup keeps your monthly spend predictable while giving your creative team plenty of options.

Setup guide

Set up Getty Images 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 Getty Images 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 Getty Images 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 Getty Images. 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 Getty Images 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 Getty Images MCP in Vercel AI SDK

Install `@ai-sdk/mcp` and call `createMCPClient` with your HTTP endpoint URL. Pass the tools array directly into `streamText` to let your agent query assets.

Yes. The agent uses `search_videos` and `get_video` to fetch video details, streaming the preview URLs directly into your React components without delay.

Yes, this MCP Server operates over lightweight HTTP transports. It is fully compatible with Edge runtimes, meaning you can search and display assets without cold-start penalties.

Configure your agent to only call `search_images` and `get_image` for previews. Restrict access to `download_image` by wrapping it in a custom tool approval step on your MCP server.

This tool only transmits search terms, page numbers, and asset IDs to the Getty API. No user-identifiable code, proprietary prompts, or layout files ever leave your local environment.

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