How to Use the Unsplash MCP in Pydantic AI

Q: How does Pydantic AI ensure data quality when searching Unsplash photos?

Pydantic validates the schema at runtime. When you call searchphotos, it verifies that every returned ID and URL matches your defined Python model, preventing bad data from moving forward.

Q: What is the most reliable way to get a full list of photos from Unsplash using Pydantic AI?

You must use listcollectionphotos with a specific collection ID. The validation layer confirms that every single item in the returned list adheres perfectly to your schema.

Q: Can I rely on the data from Unsplash when searching photographers using Pydantic AI?

Yes, you can. After calling searchphotographers, the resulting profile information is validated against your models, giving you high confidence in the attribution details.

Q: If I need to check specific photo metadata from Unsplash using Pydantic AI, what should I do?

You call getphotodetails with the ID. The tool returns a structured payload that is immediately validated by your framework before your agent uses it.

Guaranteed data structure for Unsplash assets using Pydantic AI validation in Python SDKs.

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 Pydantic AI

Create your Vinkius account to connect Unsplash to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Guarantee structured photo search results from Unsplash.

Use `search_collections` to find curated groups, but the real value comes when you validate the output. Pydantic ensures that every keyword search returns fields like ID and URL in the exact format your agent expects. Need photos based on specific criteria? Call `search_photos`. The resulting data structure is validated at runtime—no weirdly formatted photo info.

Validate all content within a Unsplash collection.

The `list_collection_photos` tool requires a Collection ID. When you run this, Pydantic validates every resulting record against your model. If one field is missing or wrong, the agent fails loudly—you know immediately. This level of strict checking means you don't have to worry about silent data corruption when processing large sets of images.

Precisely fetch and validate single Unsplash assets.

When you use `get_photo_details`, the tool returns a full record for one image. Pydantic validates every attribute, guaranteeing that data like resolution or photographer name is structured correctly. For quick checks, `get_random_photo` gives you a random asset. It's validated just as strictly, ensuring its URL and metadata are 100% reliable.

Setup guide

Set up Unsplash MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "unsplash-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Unsplash tools.",
)

result = await agent.run("List recent Unsplash transactions")
print(result.output)

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 Pydantic AI

Pydantic validates the schema at runtime. When you call `search_photos`, it verifies that every returned ID and URL matches your defined Python model, preventing bad data from moving forward.

You must use `list_collection_photos` with a specific collection ID. The validation layer confirms that every single item in the returned list adheres perfectly to your schema.

Yes, you can. After calling `search_photographers`, the resulting profile information is validated against your models, giving you high confidence in the attribution details.

You call `get_photo_details` with the ID. The tool returns a structured payload that is immediately validated by your framework before your agent uses it.

You'll be dealing with Photo IDs and URLs. These specific data types are rigorously checked to ensure they match the expected structure before your agent proceeds.

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