How to Use the Unsplash Extended MCP in LlamaIndex

Q: How do I use Unsplash Extended and LlamaIndex together for advanced discovery?

Run searchphotos first, then feed the keywords into your indexing pipeline. This allows LlamaIndex to create a searchable knowledge base that goes beyond simple API output, providing deeper context.

Q: What is the best way to use Unsplash Extended and LlamaIndex for user research?

You can index data gathered from getuser profiles alongside their activity logs. This lets your agent answer specific questions about users, like 'Which topics did this user view most often?' using grounded API data.

Q: Can I track and query download history with Unsplash Extended and LlamaIndex?

Yes. After running trackphotodownload, you can index the resulting attribution record along with the photo ID. This lets your agent answer historical questions about content usage months later.

Ground your AI client in visual data using Unsplash Extended via LlamaIndex.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Unsplash Extended MCP to LlamaIndex

Create your Vinkius account to connect Unsplash Extended to LlamaIndex 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 Extended with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Vector search with MCP Server

Instead of just running a keyword search, you can index the results from `search_photos` into your vector store. This lets your RAG application answer questions like, 'What kinds of photos are available in the city genre?' using semantic understanding. By indexing data retrieved via `get_topic`, you allow users to query concepts—not just keywords—and get answers grounded directly in Unsplash Extended's catalog.

Profiling and metrics for LlamaIndex

You can build a knowledge graph out of performance data. For example, index the results from `get_photo_statistics` alongside the user who viewed it via `get_user_statistics`. This combination lets your agent answer questions like, 'Which photos in this topic had the highest view count last month?' Indexing these metrics means you don't have to re-query them; they're right there, ready for the LLM to reference.

Managing content relationships

Don't treat collections as isolated silos. Use `get_related_collections` to find contextually linked groups and index those relationships. Your knowledge base can then answer, 'If I look at this album, what other albums should I check?' The ability to list all public groupings via `list_collections` also gives you a solid set of data points to build out your initial index.

Setup guide

Set up Unsplash Extended MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Unsplash Extended MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Unsplash Extended tools.",
)
response = await agent.run("List recent Unsplash Extended data")

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 Extended 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 Extended MCP in LlamaIndex

Run `search_photos` first, then feed the keywords into your indexing pipeline. This allows LlamaIndex to create a searchable knowledge base that goes beyond simple API output, providing deeper context.

You can index data gathered from `get_user` profiles alongside their activity logs. This lets your agent answer specific questions about users, like 'Which topics did this user view most often?' using grounded API data.

Yes. After running `track_photo_download`, you can index the resulting attribution record along with the photo ID. This lets your agent answer historical questions about content usage months later.

Absolutely. You can list photos from the general feed using `list_photos` or get a quick sample with `get_random_photo`. Both are great starting points for building out your index.

This server touches the Photo ID and User Profile. Any changes or retrievals of a user's identity are managed via `get_user` and `update_me`, making sure your index is always current.

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