How to Use the Getty Images MCP in Pydantic AI

Q: What's the difference between searchcreative and searcheditorial in the Getty Images MCP server?

The searchcreative tool finds images licensed for commercial use, like marketing materials. The searcheditorial tool finds images for newsworthy or public interest content, which cannot be used commercially. Choosing the right one is critical for legal compliance.

Add type-safe, validated Getty Images access to your Python app with Pydantic AI.

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 Pydantic AI

Create your Vinkius account to connect Getty Images to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Get Search Results You Can Trust

The `search_images` tool connects your agent to Getty's vast stock photo library. It returns data like asset IDs, titles, and preview URLs. It's a direct feed from the Getty API. Here's why you use Pydantic AI: every response is automatically parsed and validated against a Pydantic model. If the API ever returns an image with a missing caption or a malformed ID, your code raises a `ValidationError` on the spot. You get to handle the error explicitly instead of dealing with corrupted data silently breaking your app later.

Build Correct-by-Construction Media Workflows

A smart workflow separates looking from taking. Use the `get_image` tool to fetch an asset's full metadata first. This gives you all the details without touching your download quota. Only when you're sure it's the right image do you call the `download_image` tool. With Pydantic AI, you define the exact data structure you expect for that metadata. Your agent can programmatically check that an image has a valid `asset_id` and a non-empty `title` before it even considers the download. This enforces correctness at every step, making your agent's behavior predictable and reliable.

Use Any LLM with This MCP Server

This server gives you more than just search; it provides tools for discovery and management. Use `get_similar` to find visually related images or `list_collections` to work with your team's existing lightboxes. It's a complete toolset for interacting with the Getty library. The best part is that Pydantic AI is model-agnostic. You can build your agent with a model from OpenAI, Anthropic, Google, or even one running locally on your machine. The MCP server connection and the Pydantic data validation work exactly the same, no matter which LLM is making the decisions.

Setup guide

Set up Getty Images MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "getty-images-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Getty Images tools.",
)

result = await agent.run("List recent Getty Images transactions")
print(result.output)

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 Pydantic AI

Pydantic AI automatically validates every response from the Getty Images MCP server against a Pydantic model. If the data doesn't match the expected schema—for example, a required field is missing—it raises a `ValidationError` so you can handle the issue immediately.

Yes. Pydantic AI is model-agnostic, so you can connect it to any LLM, including local models run with frameworks like Ollama or llama.cpp. The Getty Images tools will function the same way.

The `search_creative` tool finds images licensed for commercial use, like marketing materials. The `search_editorial` tool finds images for newsworthy or public interest content, which cannot be used commercially. Choosing the right one is critical for legal compliance.

You instantiate it by passing your unique Vinkius server URL: `toolset = MCPToolset("https://your-vinkius-url.mcp.vinkius.com")`. Then, you pass it to your agent constructor in the `toolsets` list. Pydantic AI handles the rest.

Only the data required for a given tool is processed, such as a search phrase for a query or an asset ID for a download. The connection is secured by a single Vinkius token, and the server itself is ephemeral, meaning no data is stored after your request is complete.

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