How to Use the Flickr Photo Discovery MCP in AutoGen

Deploy AutoGen multi-agent teams that debate, filter, and select images using Flickr Photo Discovery tools.

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 AutoGen

Create your Vinkius account to connect Flickr Photo Discovery 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 Flickr Photo Discovery with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run Multi-Agent Debates on Flickr Photo Discovery

The `search_flickr_photos` tool gives your AutoGen agents the ability to scan millions of public images. One agent executes the search query while a separate critic agent reviews the results to check if they match your aesthetic criteria. This workflow stops poor-quality images from slipping through. By separating the search from the evaluation step, your agent team debates and agrees on the best visual assets before presenting them to you.

Audit Photo Metadata via MCP Server Tools

The `get_flickr_photo_info` tool gets deep technical data, including camera profiles, focal lengths, and licensing using our MCP setup. In an AutoGen setup, a compliance agent calls this tool to check if an image has the correct Creative Commons license. If the compliance agent flags a license issue, it sends a rejection back to the search agent. This feedback loop ensures your application only uses images that are legally cleared for your specific use case.

Track Live Uploads with Agent Teams

The `get_recent_flickr_photos` tool pulls the latest public uploads from the global feed. You can assign a watcher agent to watch this feed and alert other agents when new images matching specific parameters are published. This setup works for tracking breaking news or emerging visual trends. Your agents discuss the incoming photos in real-time, deciding which ones are worth analyzing further without requiring your constant supervision.

Setup guide

Set up Flickr Photo Discovery 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 Flickr Photo Discovery 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="Flickr Photo Discovery_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Flickr Photo Discovery 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="Flickr Photo Discovery_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Flickr Photo Discovery 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 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 AutoGen

Use the MCP tool adapter to convert the server tools into the format expected by the framework. Pass the adapted tools directly to your AssistantAgent during initialization so they are ready for conversation.

Yes, the server handles concurrent requests from different agents. Your search agent and your metadata auditing agent can call their respective tools at the same time without conflicts.

You can configure a group chat manager to mediate. If one agent finds an image but another agent rejects it based on metadata, they will debate until they find a photo that satisfies both constraints.

The MCP server itself is model-agnostic and focus entirely on tool execution. You define the system prompts and behavioral rules inside your agent configurations to control how they use the tools.

Your Flickr public photo metadata and search queries are processed in an isolated sandbox that gets destroyed immediately after execution. Your API key never enters the agent conversation logs, keeping your credentials safe.

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