How to Use the Getty Images MCP in LangChain

Q: How do I connect Getty Images to LangChain?

Run pip install langchain-mcp-adapters langgraph. Use MultiServerMCPClient pointing to your Vinkius endpoint, then call client.gettools() to pass the Getty functions to your ReAct agent.

Q: Can LangChain agents search Getty Images for specific collections?

Yes. The agent can execute listcollections to read your Getty lightbox data. It can then cross-reference those IDs with other chains to build targeted media lists.

Q: How does LangGraph handle Getty Images download quotas?

You map downloadimage as a separate node in your graph. Add an interrupt before that node executes so a human can approve the quota consumption.

Build multi-step reasoning pipelines with LangChain agents that search, filter, and download Getty Images assets.

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 LangChain

Create your Vinkius account to connect Getty Images to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Getty Images MCP Server tools

LangChain takes the output of one tool and feeds it directly into another. Your ReAct agent runs `search_images` to pull back asset IDs and preview URLs based on a user prompt. From there, it evaluates the results and passes the best matches into `get_images_batch` to pull full metadata before making a final selection. You do not have to write the glue code. The agent decides the execution order. If the user asks for visually related content, the chain automatically routes the chosen asset ID into `get_similar` to expand the media pool without manual intervention.

Build safe commercial asset pipelines

Stock media licensing gets complicated fast. You can configure your LangChain agent to strictly use `search_creative` for marketing copy, keeping editorial content out of commercial workflows. The agent handles the filtering logic, ensuring nobody accidentally uses a restricted news photo for an ad campaign. When the agent confirms the right asset, it triggers `download_image`. Since this consumes corporate quota limits, you can add a human-in-the-loop approval step via LangGraph before the tool executes. This keeps your budget intact while automating the discovery phase.

Trace every video and photo query

You need to know exactly what your agent is searching for and how long the Getty API takes to respond. Because this runs through LangChain, every call to `search_videos` or `get_video` is fully observable in LangSmith. You get hard numbers on performance. You will see the exact phrase passed to the search endpoint, the token usage for the LLM reasoning step, and the latency of the API response. If an agent loops repeatedly on `list_collections`, you spot the failure in the trace immediately and adjust the prompt.

Setup guide

Set up Getty Images MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Getty Images tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "getty-images-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Getty Images transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

Run `pip install langchain-mcp-adapters langgraph`. Use `MultiServerMCPClient` pointing to your Vinkius endpoint, then call `client.get_tools()` to pass the Getty functions to your ReAct agent.

Yes. The agent can execute `list_collections` to read your Getty lightbox data. It can then cross-reference those IDs with other chains to build targeted media lists.

You map `download_image` as a separate node in your graph. Add an interrupt before that node executes so a human can approve the quota consumption.

Restrict the tools you pass to the agent. If you only want commercial assets, only give the agent `search_creative` and hide `search_editorial` completely.

The server processes your search phrases, asset IDs, and lightbox collection names. Vinkius runs the connection in an ephemeral V8 Isolate Sandbox, meaning the memory wipes after the session ends. Your queries never train external models.

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