Can it automatically fetch 5 relevant images based on an abstract concept and give me direct URLs?

Yes. Command the LLM using 'search_photos' with a query like 'Serenity' and 'per_page: 5'. It leverages the native search algorithm to bring back structured output containing precise image hotlinks alongside the photographers' names for attribution.

If I am building a mock UI, can it provide a purely random high-res placeholder image?

A perfect use case! Instruct the AI to call 'get_random_photo'. It skips conventional heavy searches pulling one brilliant, random massive resolution photo. You can even filter the chaos slightly (e.g., random 'architecture').

How do I ensure I get photos only from a specific trusted photographer I like?

If you know their handle, fire off the 'get_photographer_photos' payload. The bot will bypass generic listings entirely, retrieving paginated bundles of art exclusively captured and uploaded by that precise account profile natively.

Unsplash MCP Server for Google ADK 10 tools — connect in under 2 minutes

Name: Unsplash
Availability: InStock
Author: Vinkius

google.github.io/adk-docs/tools/mcp-tools

Built by Vinkius GDPR 10 Tools SDK

Google Agent Development Kit (ADK) is Google's framework for building production AI agents. Add Unsplash as an MCP tool provider through the Vinkius and your ADK agents can call every tool with full schema introspection.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

from google.adk.agents import Agent
from google.adk.tools.mcp_tool import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import (
    StreamableHTTPConnectionParams,
)

# Your Vinkius token — get it at cloud.vinkius.com
mcp_tools = McpToolset(
    connection_params=StreamableHTTPConnectionParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    )
)

agent = Agent(
    model="gemini-2.5-pro",
    name="unsplash_agent",
    instruction=(
        "You help users interact with Unsplash "
        "using 10 available tools."
    ),
    tools=[mcp_tools],
)

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Unsplash MCP Server

Connect the Unsplash photography ecosystem to any AI agent and take full autonomous control over discovering, indexing, and retrieving high-resolution imagery and curated collections native to your chat interface.

Google ADK natively supports Unsplash as an MCP tool provider — declare the Vinkius Edge URL and the framework handles discovery, validation, and execution automatically. Combine 10 tools with Gemini's long-context reasoning for complex multi-tool workflows, with production-ready session management and evaluation built in.

What you can do

Intelligent Image Search — Query the global massive library using natural language to extract direct photo IDs, resolution properties, and immediate HD links
Curated Collection Auditing — Dive into thematic human-curated folders grabbing entire bundles of contextual visuals natively via API search_collections
Random Inspiration Hooks — Prompt the LLM to pluck out absolutely random high-res visuals based on subtle conceptual inputs finding the elusive perfect placeholder
Photographer Telemetry — Isolate public artists retrieving entire portfolios tracking the search_users capabilities inherently within your workspace

The Unsplash MCP Server exposes 10 tools through the Vinkius. Connect it to Google ADK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Unsplash to Google ADK via MCP

Follow these steps to integrate the Unsplash MCP Server with Google ADK.

Install Google ADK

Run pip install google-adk

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Create the agent

Save the code above and integrate into your ADK workflow

Explore tools

The agent will discover 10 tools from Unsplash via MCP

Why Use Google ADK with the Unsplash MCP Server

Google ADK provides unique advantages when paired with Unsplash through the Model Context Protocol.

Google ADK natively supports MCP tool servers — declare a tool provider and the framework handles discovery, validation, and execution

Built on Gemini models, ADK provides long-context reasoning ideal for complex multi-tool workflows with Unsplash

Production-ready features like session management, evaluation, and deployment come built-in — not bolted on

Seamless integration with Google Cloud services means you can combine Unsplash tools with BigQuery, Vertex AI, and Cloud Functions

Unsplash + Google ADK Use Cases

Practical scenarios where Google ADK combined with the Unsplash MCP Server delivers measurable value.

Enterprise data agents: ADK agents query Unsplash and cross-reference results with internal databases for comprehensive analysis

Multi-modal workflows: combine Unsplash tool responses with Gemini's vision and language capabilities in a single agent

Automated compliance checks: schedule ADK agents to query Unsplash regularly and flag policy violations or configuration drift

Internal tool platforms: build self-service agent platforms where teams connect their own MCP servers including Unsplash

Unsplash MCP Tools for Google ADK (10)

These 10 tools become available when you connect Unsplash to Google ADK via MCP:

get_collection_details

Retrieves details for a specific photo collection

get_photo_details

Retrieves details for a specific Unsplash photo

get_photographer_photos

Lists photos uploaded by a specific Unsplash user

get_random_photo

Optionally provide a query to narrow the random selection. Retrieves a random high-resolution photo

list_collection_photos

Requires a collection ID. Lists all photos contained within a specific collection

list_editorial_topics

Lists curated editorial topics (Nature, Architecture, etc.)

list_latest_photos

Lists the most recently uploaded photos on Unsplash

search_collections

g. "Nature", "Industrial"). Search for curated photo collections by keyword

search_photographers

Search for Unsplash photographers by name or username

search_photos

Returns photo IDs, URLs, and photographer information. Note: Proper attribution is required. Search Unsplash for free high-resolution photos

Example Prompts for Unsplash in Google ADK

Ready-to-use prompts you can give your Google ADK agent to start working with Unsplash immediately.

"Search for 3 high resolution images containing 'cyberpunk city' aesthetics and provide their URLs natively in your response."

"Grab a random photo matching 'coffee desk concept' to help me prototype a blog layout."

"I need to see what's trending. Quickly gather the 10 most recently published latest photos off the main feed."

Troubleshooting Unsplash MCP Server with Google ADK

Common issues when connecting Unsplash to Google ADK through the Vinkius, and how to resolve them.

McpToolset not found

Update: pip install --upgrade google-adk

Unsplash + Google ADK FAQ

Common questions about integrating Unsplash MCP Server with Google ADK.

How does Google ADK connect to MCP servers?

Import the MCP toolset class and pass the server URL. ADK discovers and registers all tools automatically, making them available to your agent's tool-use loop.

Can ADK agents use multiple MCP servers?

Yes. Declare multiple MCP tool providers in your agent configuration. ADK merges all tool schemas and the agent can call tools from any server in a single turn.

Which Gemini models work best with MCP tools?

Gemini 2.0 Flash and Pro models both support function calling required for MCP tools. Flash is recommended for latency-sensitive use cases, Pro for complex reasoning.