How to Use the Flickr MCP in Pydantic AI

Q: How do I configure the Flickr MCP Server in my Pydantic AI project?

You instantiate MCPToolset with your Vinkius HTTP endpoint. Then, pass that toolset object to the Agent constructor to give your model access to all 12 tools.

Q: Can my Pydantic AI agent fetch detailed metadata for a Flickr photo?

Yes, your agent can run the getphotoinfo tool to get details like owner info and EXIF data. The response is validated against a strict Pydantic model at runtime.

Build type-safe photo search pipelines with Pydantic AI validating every single Flickr API response at runtime.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Flickr MCP to Pydantic AI

Create your Vinkius account to connect Flickr 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 Flickr with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Strictly validated photo search via Pydantic AI

This MCP Server exposes `search_photos` as the primary entry point for querying Flickr's public database, returning structured image data directly to your agent. When using Pydantic AI, every returned photo object is validated against strict schemas before your agent even sees it. If Flickr's API structure changes or returns unexpected null values, the framework raises a validation error immediately. Catching these validation errors early prevents corrupted data from propagating through your processing pipeline.

Safe album inspection with runtime validation

The `get_album_photos` tool retrieves all images contained within a specific public Flickr album. Compiling reference galleries or analyzing curated collections is simple with this setup. By routing this tool through Pydantic AI, you ensure that every image ID, title, and URL matches your expected Python types. Feeding the resulting data directly into downstream database models is completely safe once validated.

Real-time trend analysis using this MCP Server

The `get_hot_tags` tool fetches the most popular tags currently trending across the Flickr platform. Discovering what subjects are gaining traction in real time is incredibly fast. Because the framework is model-agnostic, you can use this MCP Server with any LLM while maintaining strict type safety. Validating the returned tags instantly ensures your trend-tracking scripts never crash due to dirty data.

Setup guide

Set up Flickr 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": {
        "flickr-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Flickr 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 Flickr. 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 Flickr 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 Flickr MCP in Pydantic AI

You instantiate `MCPToolset` with your Vinkius HTTP endpoint. Then, pass that toolset object to the `Agent` constructor to give your model access to all 12 tools.

Yes, your agent can run the `get_photo_info` tool to get details like owner info and EXIF data. The response is validated against a strict Pydantic model at runtime.

The framework will raise a validation error instantly. This ensures your agent never processes malformed or incomplete data from tools like `get_recent_photos`.

Yes, the toolset runs asynchronously over HTTP or SSE transports. This allows your agent to fetch album lists and photo details concurrently without blocking.

Vinkius handles the storage and injection of your Flickr API credentials securely. Only public search queries and public photo IDs are transmitted, and no sensitive account data is ever exposed to the model.

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