How to Use the Unsplash Extended MCP in LangChain

Q: How do I use Unsplash Extended and LangChain together to find visually related content?

Use a chain that first runs searchphotos based on user input. Next, pass the resulting photo IDs into getrelatedcollections to surface contextually relevant groups of images. This gives you much more than just simple keyword matching.

Q: How can I track attribution for content using Unsplash Extended and LangChain?

Always use trackphotodownload immediately after a download occurs. This specific tool is required to log usage data, ensuring you get accurate metrics. Your agent makes sure this happens every time.

Q: Does the MCP Server support listing all available photo sources?

Yep. You can use listphotos to grab a dump of photos from the editorial feed, or you might prefer using getrandomphoto if you just need filler content for testing.

Build complex photo research pipelines with LangChain's multi-step reasoning.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Unsplash Extended MCP to LangChain

Create your Vinkius account to connect Unsplash Extended 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 Unsplash Extended with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Discover content using MCP Server

You can design a chain that starts by listing general options, like `list_topics`, and then narrows the focus. For example, an initial search for `search_photos` gets keywords, which you feed into `get_topic_photos` to find specific visual matches. This sequential approach means your agent doesn't just call one API; it uses the output from a photo listing to determine which related collection to check via `get_related_collections`. It’s all about flow.

Manage collections and users

Need to organize assets? You can build a sequence that first calls `list_user_collections` to see what's available. Then, if the user needs something new, your agent executes `create_collection`. Finally, it uses `add_photo_to_collection` to populate it with images retrieved by ID. If an existing collection is wrong, you don't have to rebuild it. You just use `update_collection`, or if the photo needs removal entirely, call `remove_photo_from_collection`. It keeps the workflow tight.

Track engagement and profile data

This is key for attribution. Your agent can check a photo's performance by calling `get_photo_statistics`, letting you know how many times it was viewed or downloaded. You can then use that data to suggest actions, like having the user `like_photo` if the image is highly relevant. It also handles profile management; your agent first runs `get_me` for current user details. If changes are needed, calling `update_me` keeps the user's record synced with Unsplash Extended.

Setup guide

Set up Unsplash Extended 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 Unsplash Extended 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({
    "unsplash-extended-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 Unsplash Extended 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 Unsplash. 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 Unsplash Extended 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 Unsplash Extended MCP in LangChain

Use a chain that first runs `search_photos` based on user input. Next, pass the resulting photo IDs into `get_related_collections` to surface contextually relevant groups of images. This gives you much more than just simple keyword matching.

You can build a multi-step process: list all existing collections using `list_user_collections`, then check if new photos need grouping by calling `get_topic_photos`. This determines if you should run `create_collection` or just add the assets.

Always use `track_photo_download` immediately after a download occurs. This specific tool is required to log usage data, ensuring you get accurate metrics. Your agent makes sure this happens every time.

Yep. You can use `list_photos` to grab a dump of photos from the editorial feed, or you might prefer using `get_random_photo` if you just need filler content for testing.

This server handles your authenticated user profile. Any updates or retrievals use the user's unique ID, which is managed through the `get_me` and `update_me` tools.

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