How to Use the Unsplash MCP in LangChain

Q: How do I find a specific collection in Unsplash using LangChain?

First, you run searchcollections with keywords like 'food' or 'portrait'. The output gives you the IDs of potential collections. You then feed one of those IDs into getcollectiondetails to verify it’s the right one for your project.

Q: What is the best way to get random, high-res photos with Unsplash and LangChain?

Just call the simple function, getrandomphoto. It doesn't need complex setup. You can even narrow that random selection by passing a query string when you make the initial tool call.

Q: Can I list all photos from a specific collection in Unsplash using LangChain?

Yep, use listcollectionphotos. It requires a collection ID as input. The function returns an array of every photo within that boundary, making it easy to process them sequentially.

Q: If I run a search for Unsplash using LangChain, what information do I get?

The searchphotos tool returns three key pieces of data: the photo ID, the direct URL to the image, and the associated photographer's information. This is crucial for proper attribution.

Build multi-step photo pipelines in your chains using the Unsplash MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Unsplash MCP to LangChain

Create your Vinkius account to connect Unsplash 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 with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate image searches and discovery.

Need a random, high-res shot? Call `get_random_photo` to grab immediate inspiration. Or, if you're building something specific, run `search_photos`. This gives you photo IDs, URLs, and attribution info all in one go. You can then use that output—say, the ID from a search—as the input for another tool call, like checking out related photos using `get_photo_details`.

Structure photo content by collection.

When you know the theme, start with collections. You can use `search_collections` to find curated groups (like 'Nature' or 'Industrial'). Once you have a collection ID, run `get_collection_details` to see what it covers. To get every single photo in that group, just hit up `list_collection_photos`. The chain handles pulling all those IDs and compiling them into one list for your agent.

Find photographers and their work.

Want to credit the right person? Start by finding a photographer using `search_photographers` with their name or username. That tool gives you their profile info. After that, run `get_photographer_photos`. The resulting list of photo details allows your chain to build out an entire portfolio view for attribution purposes.

Setup guide

Set up Unsplash 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 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-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 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 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 MCP in LangChain

First, you run `search_collections` with keywords like 'food' or 'portrait'. The output gives you the IDs of potential collections. You then feed one of those IDs into `get_collection_details` to verify it’s the right one for your project.

Just call the simple function, `get_random_photo`. It doesn't need complex setup. You can even narrow that random selection by passing a query string when you make the initial tool call.

Yep, use `list_collection_photos`. It requires a collection ID as input. The function returns an array of every photo within that boundary, making it easy to process them sequentially.

This MCP Server handles metadata about photos, collections, and users. Specifically, it manages photo IDs, URLs, collection names, photographer usernames, and descriptive topics.

The `search_photos` tool returns three key pieces of data: the photo ID, the direct URL to the image, and the associated photographer's information. This is crucial for proper attribution.

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