4,500+ servers built on MCP Fusion
Vinkius
Unsplash logo
Vinkius
Claude Code logo

How to Use the Unsplash MCP in Claude Code

Run visual content pipelines with Claude Code. Headless image sourcing for CI/CD and scripting.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

Unsplash MCP on Cursor AI Code Editor MCP Client Unsplash MCP on Claude Desktop App MCP Integration Unsplash MCP on OpenAI Agents SDK MCP Compatible Unsplash MCP on Visual Studio Code MCP Extension Client Unsplash MCP on GitHub Copilot AI Agent MCP Integration Unsplash MCP on Google Gemini AI MCP Integration Unsplash MCP on Lovable AI Development MCP Client Unsplash MCP on Mistral AI Agents MCP Compatible Unsplash MCP on Amazon AWS Bedrock MCP Support
MCP Servers - Free for Subscribers
Claude Code

Connect Unsplash MCP to Claude Code

Create your Vinkius account to connect Unsplash to Claude Code 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

MCP Server: Scripting photo searches for Claude Code

Use `search_photos` directly in your shell script to pull Unsplash IDs, URLs, and photographer information. The output is pure JSON that can be piped into a logging or database tool. You don't need a graphical interface; you just run the command line invocation, and the MCP Server provides the raw data needed for automated pipelines.

Batch listing assets with MCP Server for Claude Code

If your workflow requires processing every photo in an existing set, call `list_collection_photos` using a collection ID. This function returns a list of IDs that you can iterate over within a cron job or GitHub Action. You can then use these batch IDs to run subsequent commands against the server, making it perfect for bulk content processing.

Automating random asset generation with MCP Server and Claude Code

Need a diverse set of images without specifying keywords? Use `get_random_photo` to retrieve a high-resolution photo directly from the terminal. The result is instantly usable in your script for testing purposes. This capability allows you to test content pipelines using real, unpredictable data streams, ensuring robustness.

Setup guide

Set up Unsplash MCP in Claude Code

Prerequisites

  • Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
  • Active Vinkius subscription with a valid endpoint token
  1. 1

    Run the add command

    Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.

  2. 2

    Verify the connection

    Start a Claude Code session and type /mcp to list connected servers. You should see unsplash-mcp with a green status indicator.

  3. 3

    Start using tools

    Ask Claude Code something like "Check my latest Unsplash transactions." It will automatically discover and invoke the available Unsplash tools.

Terminal
claude mcp add --transport http unsplash-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

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 MCP in Claude Code

You invoke the `search_photos` tool within your shell script. The server executes the query headless and outputs structured data that other tools (like sed or jq) can consume directly.
This MCP Server accesses photo metadata (IDs, URLs), photographer usernames, and collection structures. Because it’s terminal-based, the focus is entirely on machine-readable output.
Yes. You use `search_collections` to find multiple keywords and process them sequentially within a single script run. This makes it great for building asset inventories across many topics.
It is dependable for scripting because the output format is consistent JSON data. You can reliably test image sourcing within a Docker container or GitHub Action without relying on any GUI elements.
The `search_photos` tool ensures proper attribution is returned as part of the data payload. This guarantees that your scripts log or save necessary credit information alongside every photo ID.

Start using the Unsplash MCP today

We host it, we monitor it, we maintain it. You just paste one token.

Built & Managed by Vinkius 30s setup 10 tools

We've already built the connector for Unsplash. Just plug in your AI agents and start using Vinkius.

No hosting. No infrastructure. No complex setup.
All 10 tools are live and waiting. You're up and running in seconds.

Claude Claude
ChatGPT ChatGPT
Cursor Cursor
Gemini Gemini
Windsurf Windsurf
VS Code VS Code
JetBrains JetBrains
Vercel Vercel
+ other MCP clients

Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.

Zero hosting required Full MCP catalog included Enterprise-grade security Auto-updated by Vinkius

Built, hosted, and secured by Vinkius. You just connect and go.