How to Use the Flickr Photo Discovery MCP in LangChain

Build multi-step LangChain pipelines that search, analyze, and trace Flickr Photo Discovery queries with zero-latency overhead.

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 LangChain

Create your Vinkius account to connect Flickr Photo Discovery to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Composable Photo Pipelines in LangChain

The `search_flickr_photos` tool lets your agent find public images based on specific search terms. You chain this output directly into subsequent nodes, letting your agent evaluate composition or pull source images without writing custom API logic. LangChain handles the flow so the search results instantly feed your next prompt. You can run automated checks or build multi-step chains that decide which photo to analyze next based on its initial tags.

Extract Real-Time EXIF Data with this MCP Server

The `get_flickr_photo_info` tool gets deep technical metadata, including camera models, exposure settings, and license details. Your agent parses this raw JSON payload to filter out low-quality shots or check Creative Commons compliance before displaying results. Because this MCP Server runs in an isolated sandbox, your pipeline stays secure while fetching external web data. You get clean, structured metadata delivered straight to your model, avoiding the usual parsing headaches of raw scraping.

Track Fresh Public Uploads

The `get_recent_flickr_photos` tool pulls the latest public uploads directly from the global feed. Your agent monitors this stream using the MCP connection to analyze current photographic trends or track specific tags. You can track this whole ingestion pipeline using LangSmith to watch latency and token usage. Every single tool call shows up in your logs, showing you exactly how your agent interacts with the live photo feed.

Setup guide

Set up Flickr Photo Discovery MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Flickr Photo Discovery tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "flickr-photo-discovery-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Flickr Photo Discovery transactions"
    })
    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 LangChain

Install the adapter package and initialize the client with your endpoint. Call the tool getter and pass the resulting list directly into your agent constructor to let it choose when to search or pull metadata.

Yes, every call to these tools registers inside LangSmith automatically. You can inspect the exact payload, execution time, and token cost for every search or metadata query your agent runs.

The server operates statelessly by default to keep operations fast. You can use the client session manager if you need to maintain context across multiple sequential photo queries.

The adapter handles basic API backoff behind the scenes. If your agent triggers a rate limit while fetching public feeds, the framework catches the error and lets you define custom retry logic.

We never store your search parameters or the public image metadata retrieved from the API. All requests pass through an ephemeral V8 sandbox that wipes your session data the moment the tool execution finishes.

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