How to Use the Getty Images MCP in OpenAI Agents SDK

Q: How do I use the OpenAI Agents SDK to search Getty Images for commercial-use photos?

Your agent should use the searchcreative tool. This tool specifically targets Getty's library of images that are cleared for commercial and marketing purposes, which keeps your projects compliant.

Q: Can my agent download multiple images at once?

No, the downloadimage tool processes one asset ID at a time to ensure downloads are intentional and tracked against your quota. For fetching metadata in bulk, you should use the getimagesbatch tool.

Q: How does the OpenAI Agents SDK handle the difference between creative and editorial images from Getty Images?

The MCP server exposes two distinct tools: searchcreative for commercial use and searcheditorial for newsworthy content. Your agent's logic must choose the correct tool based on the task to avoid licensing issues.

Q: What's the best way to preview an image from Getty Images before my OpenAI agent downloads it?

First, use searchimages to get a list of asset IDs. Then, pass those IDs to getimage or getimagesbatch. This returns preview URLs and metadata without consuming your expensive download credits.

Build production agents with the OpenAI Agents SDK that search and download from your Getty Images account.

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 OpenAI Agents SDK

Create your Vinkius account to connect Getty Images to OpenAI Agents 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Find the Right Image, Every Time

This MCP server gives your agent direct access to Getty's library. You can run targeted searches for commercial-use photos with `search_creative` or news-specific content with `search_editorial`. The `search_images` tool returns a clean list of asset IDs and preview URLs, which is exactly what an agent needs to start working. With the OpenAI Agents SDK, you can build multi-agent systems that use these tools. For example, one agent can run the initial `search_images` query, then hand off the results to a second, specialized agent whose only job is to analyze the image captions for brand safety before presenting them to the user. It's a solid way to break down complex creative tasks.

Control Costs with Gated Downloads

The `download_image` tool is powerful — it returns a direct download URL and consumes your corporate quota. Using it carelessly gets expensive, fast. This server encourages a safer workflow: first call `get_image` or `get_images_batch` to fetch metadata and low-res previews. Your agent shows these to the user for confirmation. This is where the OpenAI Agents SDK's guardrails are perfect. You can write a rule that prevents an agent from calling the `download_image` tool without explicit human approval. This simple check gives you full control over your Getty Images budget, preventing accidental or unnecessary high-res downloads.

Integrate Video and Collections with Your OpenAI Agents SDK

Your agents aren't limited to static photos. Use the `search_videos` and `get_video` tools to find and retrieve details about stock video footage. The agent gets all the metadata it needs to decide if a clip fits the project brief. Discovery doesn't stop at the first search. If an image is close but not quite right, the `get_similar` tool finds visually related options. For existing workflows, your agent can use `list_collections` to see the lightboxes you've already built on Getty's website, letting it organize new assets right alongside your team's curated content.

Setup guide

Set up Getty Images MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Getty Images tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Getty Images tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Getty Images tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Getty Images Agent",
            instructions="You have access to Getty Images tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Your agent should use the `search_creative` tool. This tool specifically targets Getty's library of images that are cleared for commercial and marketing purposes, which keeps your projects compliant.

No, the `download_image` tool processes one asset ID at a time to ensure downloads are intentional and tracked against your quota. For fetching metadata in bulk, you should use the `get_images_batch` tool.

The MCP server exposes two distinct tools: `search_creative` for commercial use and `search_editorial` for newsworthy content. Your agent's logic must choose the correct tool based on the task to avoid licensing issues.

First, use `search_images` to get a list of asset IDs. Then, pass those IDs to `get_image` or `get_images_batch`. This returns preview URLs and metadata without consuming your expensive download credits.

The server only processes the data needed for each specific action, like your search phrases or the asset IDs you want to download. Vinkius handles authentication with a single endpoint token, and the MCP server itself runs in a zero-trust, ephemeral sandbox, so your data isn't stored.

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