How to Use the Getty Images MCP in Google ADK

Q: How can my Google ADK agent search Getty Images and use the results in BigQuery?

The agent can use tools like searchimages to get asset IDs and metadata. Then, your agent's code can execute a SQL query to write those asset IDs and preview URLs into a designated BigQuery table, linking them to your internal data.

Q: Does the Google ADK integration for Getty Images support video search?

Yes. Your agent can use the searchvideos tool to find video clips and the getvideo tool to retrieve detailed metadata about them, just like it does for images.

Connect your Google ADK agents to your Getty Images account for enterprise-scale creative workflows.

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 Google ADK

Create your Vinkius account to connect Getty Images to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Drive Image Search from Your Data

This server exposes Getty's core search functions to your agent. Use `search_images` for general queries or `search_creative` for photos you can use in marketing. The tools return asset IDs, titles, and other metadata, ready for processing. Connect this to your existing Google Cloud data. A Gemini-powered agent can read a list of product SKUs from a BigQuery table, generate a search phrase for each one, and use the `search_creative` tool to find matching lifestyle photos. The agent can then write the best asset ID back into BigQuery, automating your content pipeline.

Enforce Licensing Rules at Scale

Misusing stock photos is a real legal risk. This MCP server makes the distinction clear by providing separate `search_creative` and `search_editorial` tools. Editorial images are for news and events; they are not for commercial use. Your agent needs to know the difference. This is a problem for Google's long-context models. An ADK agent can read an entire project brief from Google Docs, understand the context (e.g., 'marketing campaign' vs. 'internal news update'), and then correctly choose the `search_creative` tool. It's about building compliance directly into your automated workflow.

Manage Media Assets with Your MCP Server

Go beyond simple search and download. This server provides tools to manage the full media lifecycle. Your agent can use `search_videos` and `get_video` to find video clips and analyze their metadata before committing to a download. It also integrates with your team's existing process. The `list_collections` tool lets an agent see the lightboxes your creative team has already curated on the Getty Images website. Your agent can then add newly found assets to the appropriate collection, making it a true collaborator.

Setup guide

Set up Getty Images MCP in Google ADK

Prerequisites

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

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Getty Images tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Getty Images_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Getty Images tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

The agent can use tools like `search_images` to get asset IDs and metadata. Then, your agent's code can execute a SQL query to write those asset IDs and preview URLs into a designated BigQuery table, linking them to your internal data.

You risk a copyright claim and legal action from the image owner. The `search_editorial` tool is provided for non-commercial use only, like news reporting. For marketing, always use `search_creative`.

Yes. Your agent can use the `search_videos` tool to find video clips and the `get_video` tool to retrieve detailed metadata about them, just like it does for images.

Implement a two-step process in your agent's logic. First, use `get_image` to fetch a preview. Only after user confirmation or passing a logic check should the agent be allowed to call the `download_image` tool, which consumes quota.

It processes only the data required for an API call, like asset IDs for downloads or the names of your collections. The server runs in an isolated V8 sandbox, and Vinkius manages all authentication, so your API keys and data are not exposed.

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