How to Use the Flickr Photo Discovery MCP in OpenAI Agents SDK

Q: How do I configure Flickr Photo Discovery inside the OpenAI Agents SDK?

Install openai-agents via pip and initialize the MCP server stream using MCPServerStreamableHttp. Pass the server instance directly in the mcpservers list when creating your Agent. The agent automatically discovers the three photography tools.

Q: Does Flickr Photo Discovery support tool-call caching with the OpenAI Agents SDK?

Yes. You can set cacheToolsList=True in your SDK configuration to prevent redundant schema lookups. This keeps your agent's response times low while searching or fetching photo metadata.

Query public photography records directly from your OpenAI Agents SDK workflows with auto-discovered tools and built-in guardrails.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Flickr Photo Discovery MCP to OpenAI Agents SDK

Create your Vinkius account to connect Flickr Photo Discovery to OpenAI Agents SDK 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 Photo Discovery with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run `search_flickr_photos` with OpenAI Agents SDK

The `search_flickr_photos` tool lets your agent query millions of public Flickr images using precise text and tag parameters. By declaring this tool inside your agent's constructor, the model automatically extracts search terms from user conversations and executes the query without manual JSON parsing. Your production system benefits from immediate execution tracing on the OpenAI dashboard. The SDK manages standard HTTP transport under the hood, passing raw photo payloads directly to the agent so it can analyze image lists, verify licenses, or select the best visual matches.

Fetch real-time feeds using `get_recent_flickr_photos`

The `get_recent_flickr_photos` tool pulls the latest public photography stream directly into your agent's context window. Instead of writing custom polling scripts, you pass this MCP server endpoint to the agent stream to capture fresh image submissions as they happen. This setup avoids stale data issues by bypassing local database caches entirely. The model evaluates the raw stream metadata on the fly, allowing you to build real-time monitoring tools or automated curation pipelines with minimal latency.

Inspect image metadata with `get_flickr_photo_info`

The `get_flickr_photo_info` tool retrieves specific photographic metadata including exposure settings, camera models, and creator details. Your agent invokes this tool to verify image properties before presenting them to users or logging them in your database. Because the OpenAI Agents SDK supports runtime guardrails, you can intercept these metadata requests to enforce strict licensing checks. The agent analyzes the returned payload to ensure only Creative Commons images pass through your production pipeline.

Setup guide

Set up Flickr Photo Discovery MCP in OpenAI Agents SDK

Prerequisites

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

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Flickr Photo Discovery tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Flickr Photo Discovery tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Flickr Photo Discovery tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Flickr Photo Discovery Agent",
            instructions="You have access to Flickr Photo Discovery tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 Photo Discovery 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 Photo Discovery MCP in OpenAI Agents SDK

Install `openai-agents` via pip and initialize the MCP server stream using `MCPServerStreamableHttp`. Pass the server instance directly in the `mcp_servers` list when creating your Agent. The agent automatically discovers the three photography tools.

Yes. You can set `cacheToolsList=True` in your SDK configuration to prevent redundant schema lookups. This keeps your agent's response times low while searching or fetching photo metadata.

The SDK handles standard HTTP errors, but you should implement custom backoff logic in your agent's system prompt or loop. If `search_flickr_photos` returns a rate limit error, the agent can pause or retry.

No. Vinkius manages the API key and authentication on its hosted platform. Your Python agent only needs a single MCP endpoint token to securely access all three photography tools.

The server only processes public photo metadata and search queries. Your search queries and API endpoint tokens are never stored by Vinkius; they are passed directly to Flickr's public API endpoints over encrypted HTTPS connections.

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