Command Palette

Search for a command to run...

Home / Servers

immich-curator-mcp

Updated today

by gist-info

Immich Smart Curator: AI-Powered Photo Management & Automated Gallery Publishing

Download

A next-generation MCP (Model Context Protocol) server that transforms your Immich photo library into a living, breathing digital archive. Imagine having a personal photo curator who never sleeps—automatically organizing your memories into intelligent geographic albums, detecting duplicates with surgical precision, and publishing polished galleries for the world to see. Welcome to the future of photo management.


Quick Start: Two Minutes to a Smarter Library

Download

Example Profile Configuration

# config/profile.yaml
server:
  name: "smart-curator"
  version: "1.0.0"
  immich:
    host: "https://your-immich-instance.local"
    api_key: "${IMMICH_API_KEY}"
  curation:
    duplicate_threshold: 0.85
    geo_clustering_radius_km: 50
    auto_publish: true
  ai:
    provider: "openai" # or "claude"
    api_key: "${AI_API_KEY}"

Example Console Invocation

$ immich-smart-curator --profile config/profile.yaml \
  --action scan-library \
  --target-album "2026 Summer Adventures" \
  --publish-conflicts auto-merge

System Architecture Diagram

graph TD
    A[Immich Photo Library] --> B[Smart Curator MCP Server]
    B --> C[Duplicate Detection Engine]
    B --> D[Geographic Clustering Module]
    B --> E[Gallery Publisher]
    C --> F[Conflict Resolution AI]
    D --> G[Map Tile Generator]
    E --> H[Public Gallery CDN]
    F --> I[OpenAI API / Claude API]
    G --> J[Leaflet.js Interactive Maps]
    H --> K[Responsive Web Gallery]
    style B fill:#4CAF50,color:white
    style C fill:#2196F3,color:white
    style D fill:#FF9800,color:white
    style E fill:#9C27B0,color:white

✨ Feature List: What Makes This Different?

  • Intelligent Duplicate Hunting 🕵️ – Scans perceptual hashes and metadata to find near-identical photos, even across different resolutions or crops.
  • Geographic Album Curation 🗺️ – Automatically groups photos based on GPS coordinates, creating travel albums that tell a story of your journey.
  • One-Click Gallery Publishing 📤 – Exports curated collections as standalone, responsive web galleries deployable to any static hosting service.
  • AI-Powered Conflict Resolution 🤖 – When duplicates or overlapping albums are detected, the AI (OpenAI or Claude) proposes the best merge strategy.
  • Multilingual Metadata Support 🌍 – Reads and writes metadata in 50+ languages, ensuring your Japanese cherry blossom photos are tagged correctly even if your system language is English.
  • 24/7 Daemon Mode 🕐 – Runs as a background service, continuously monitoring your Immich library for new imports and applying curation rules automatically.
  • Responsive Web Galleries 📱 – Galleries look stunning on mobile, tablet, and desktop with built-in lazy loading and image optimization.
  • Privacy-First Architecture 🔒 – All AI processing happens via encrypted API calls; no photos are ever stored on third-party servers.

🖥️ OS Compatibility

Operating System2026 SupportRecommended RAMNotes
Windows 11/104 GBNative binary
macOS Sonoma+4 GBHomebrew install
Ubuntu 24.04+2 GBDocker or snap
Fedora 40+2 GBRPM package
Raspberry Pi OS1 GBARM64 build
Docker (any host)2 GBRecommended

🔌 API Integration: OpenAI & Claude

Related servers

n8n

Updated today

by n8n-io

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

204,501

mcp-server-fetch

OfficialUpdated 14d ago

by modelcontextprotocol

A Model Context Protocol server providing tools to fetch and convert web content for usage by LLMs

90,371

@modelcontextprotocol/server-everything

OfficialUpdated 14d ago

by modelcontextprotocol

MCP server that exercises all the features of the MCP protocol

90,371

mcp-server-git

OfficialUpdated 14d ago

by modelcontextprotocol

A Model Context Protocol server providing tools to read, search, and manipulate Git repositories programmatically via LLMs

90,371