How to Use the Unsplash Extended MCP in CrewAI

Q: How do I run a full Unsplash Extended search with CrewAI?

You assign different roles. One agent searches using searchphotos, and another processes the list by calling getphoto for individual details. This multi-agent approach makes the process robust.

Run autonomous photo operations with CrewAI and Unsplash Extended.

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 CrewAI

Create your Vinkius account to connect Unsplash Extended to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Autonomous Photo Discovery MCP Server

You set up a crew where one agent searches for images, and another analyzes the results. For example, Agent A calls `search_photos` with 'nature,' while Agent B uses that output to call `get_related_collections`. This simulates human collaboration. The shared memory feature lets agents pass photo IDs or topic names between roles, making the operational pipeline feel genuinely autonomous.

Multi-Agent User Management

Use a crew to manage user assets. Agent A can research public users using `search_users`. Then, Agent B takes that list and calls `get_user` for detailed profiles, ensuring the entire operational sequence is logged. The hierarchical execution model means you can assign one agent (the monitor) to watch all actions taken by others, logging every call to tools like `list_user_collections`.

Advanced Content Curation Tools

Build a process where an agent first gathers ideas using `get_topic`, and then another agent uses that topic ID to fetch many photos via `get_topic_photos`. This is a perfect example of sequential, specialized action. The crew structure handles the passing of context—the list of photo IDs or topics—from one specialist agent to the next without needing manual code intervention.

Setup guide

Set up Unsplash Extended MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Unsplash Extended tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Unsplash Extended Analyst",
    goal="Access and analyze Unsplash Extended data via MCP.",
    backstory="Expert analyst with direct Unsplash Extended access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Unsplash Extended transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

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

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Unsplash Extended Analyst",
        goal="Access and analyze Unsplash Extended data via MCP.",
        backstory="Expert analyst with direct Unsplash Extended access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Unsplash Extended transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

You assign different roles. One agent searches using `search_photos`, and another processes the list by calling `get_photo` for individual details. This multi-agent approach makes the process robust.

You can assign an agent a specific role: 'Collection Manager.' Give it access to `create_collection` and `list_user_collections`. The crew handles the permissions and ensures that all updates are logged.

Yes. You can make a dedicated 'Attribution Agent' whose only job is to call `track_photo_download` immediately after any successful action, ensuring the data is logged every time.

You set up a 'Reporting Agent.' This agent calls tools like `get_user_statistics` or `list_photos`. The specialized role ensures the data is handled correctly for reporting purposes.

This server touches Photo Metadata, User Profile, and Collection Data. Because you're running autonomous operations, the crew needs to handle user authentication details securely for every tool call.

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