How to Use the Unsplash MCP in AutoGen

Q: How do I find creative collections in Unsplash using AutoGen?

You can assign one agent to run searchcollections with keywords. The resulting list is then passed to a second agent, which uses the IDs to execute getcollectiondetails. They discuss and agree on the best option.

Q: What if I need random photo ideas in Unsplash using AutoGen?

One agent calls getrandomphoto. A second agent then takes that output and uses it to suggest related topics by calling listeditorialtopics for a more comprehensive result.

Q: If I run a search for Unsplash using AutoGen, what information is exchanged?

The searchphotos tool provides photo IDs, URLs, and photographer data. The agents use this raw output to debate the best attribution method and structure your final result.

Build consensus-driven creative pipelines with Unsplash using AutoGen.

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 AutoGen

Create your Vinkius account to connect Unsplash to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Delegate photo research to multiple agents.

Set up a 'Search Agent' and give it `search_collections` and `list_editorial_topics`. It finds potential themes. A second 'Review Agent' can then use that list as input for `get_collection_details`. The two agents debate the best collection, converging on the most suitable ID to move forward with.

Verify photo attribution using consensus.

One agent runs `search_photos`, generating a list of candidates. A second 'Attribution Agent' uses that data and checks specific details via `get_photo_details` to confirm the photographer name. The negotiation between agents ensures you don't miss critical attribution information before finalizing your output.

Plan multi-step content pipelines.

An 'Inspiration Agent' runs `get_random_photo`. It gets the URL and ID. A second 'Expansion Agent' takes that result and uses it to call `list_collection_photos` for related context. The agents collaborate, generating a full story—the random shot plus its surrounding collection data.

Setup guide

Set up Unsplash MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Unsplash tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Unsplash_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Unsplash data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Unsplash_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Unsplash data")
    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 AutoGen

You can assign one agent to run `search_collections` with keywords. The resulting list is then passed to a second agent, which uses the IDs to execute `get_collection_details`. They discuss and agree on the best option.

Yes. You can set up agents to negotiate between using a general search (`search_photos`) versus focusing on user-specific portfolios via `get_photographer_photos` until consensus is reached.

One agent calls `get_random_photo`. A second agent then takes that output and uses it to suggest related topics by calling `list_editorial_topics` for a more comprehensive result.

The MCP Server provides structured metadata: photo IDs, URLs, collection details, photographer usernames, and curated topics. These are the inputs for agent deliberation.

The `search_photos` tool provides photo IDs, URLs, and photographer data. The agents use this raw output to debate the best attribution method and structure your final result.

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