How to Use the Unsplash Extended MCP in AutoGen

Q: What is the best way to use Unsplash Extended and AutoGen for content planning?

Have one agent list all available topics using listtopics, while a second agent checks photo counts for specific groups via gettopicphotos. The debate centers on which combination of topic/photo density represents the biggest opportunity.

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

It does. You can use listphotos for a feed snapshot, or if you need highly specific images, running searchusers and then checking their uploaded work via listuserphotos works great.

Let your AI clients debate the best images using Unsplash Extended and 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 Extended MCP to AutoGen

Create your Vinkius account to connect Unsplash Extended 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 Extended with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debate image selection with MCP Server

Set up a group where one agent uses `search_photos` to propose a set of candidates. A second agent can then challenge that proposal by calling `get_topic_photos`, checking if the initial results are too broad or off-topic. A third agent, acting as a validator, might use `get_photo_statistics` on the finalists to argue which image has proven popularity and should be chosen for the final output.

Negotiate content strategy with AutoGen

Need help deciding if a user needs a new album? Agent 1 can list existing collections using `list_user_collections`. Agent 2 then assesses whether any photos need removal by calling `remove_photo_from_collection`, forcing the system to decide on necessary updates. The debate converges when agents decide whether to call `create_collection` or just modify an existing one via `update_collection`.

Validate user actions and permissions

You can simulate a content approval workflow. Agent A checks the current owner's rights using `get_me`. If everything looks good, Agent B proposes liking an image via `like_photo`. This forces a deliberation: is the action appropriate given the user's profile? The system uses these tools to ensure that actions like adding assets (`add_photo_to_collection`) are always validated against the authenticated user’s permissions.

Setup guide

Set up Unsplash Extended 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 Extended 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 Extended_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Unsplash Extended 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 Extended_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

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

You can set up a group where one agent fetches diverse images using `get_random_photo`, while another agent checks the required topic alignment via `get_topic`. The agents then argue over which pool of photos makes the strongest case.

Have one agent list all available topics using `list_topics`, while a second agent checks photo counts for specific groups via `get_topic_photos`. The debate centers on which combination of topic/photo density represents the biggest opportunity.

Yes. A consensus-driven process can be built where one agent tracks a download using `track_photo_download`, while another verifies that the necessary attribution data is captured before finalizing the transaction.

It does. You can use `list_photos` for a feed snapshot, or if you need highly specific images, running `search_users` and then checking their uploaded work via `list_user_photos` works great.

This server touches the User Profile. All management of who owns content or whose details are stored happens through tools like `get_user` and `update_me`, ensuring consensus on identity.

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