Immich MCP Server
Enables MCP-compatible clients to interact with an Immich photo management instance, providing access to users, assets, API keys, and partners through standardized resources and tools.
README
Immich MCP Server
This project provides a Model Context Protocol (MCP) server for the Immich photo management system. It allows you to interact with your Immich instance using MCP-compatible clients.
Features
The server exposes the following MCP resources and tools:
Resources
user://me: Get details about the current user.users://list: Get a list of all users on the Immich instance.partners://list: Get a list of all partners.asset://{asset_id}: Get details for a specific asset (photo or video) by its ID.apikey://me: Get details about the API key currently being used.apikeys://list: Get a list of all API keys.apikey://{api_key_id}: Get details for a specific API key by its ID.
Tools
ping(): A simple tool to check if the server can successfully connect to the Immich instance. Returns"pong"on success.
Deployment (Recommended)
The easiest way to deploy the Immich MCP server is by using Docker. A docker-compose.yml file is provided for your convenience.
-
Create a
.envfile: Copy the provided.env.exampleto a new file named.env:cp .env.example .envThen, edit the
.envfile to set the required environment variables. -
Run the server:
docker-compose up -dThe server will be available at
http://localhost:8000.
You can view the server logs with:
docker-compose logs -f
Official container images are available on Docker Hub and ghcr.io.
Configuration
The server is configured using environment variables:
| Variable | Description | Default | Required |
|---|---|---|---|
IMMICH_BASE_URL |
The base URL of your Immich instance (e.g., http://immich.local:2283). |
Yes | |
IMMICH_API_KEY |
Your Immich API key. | Yes | |
IMMICH_MCP_PORT |
The port on which the server will listen. | 8626 |
No |
IMMICH_MCP_TIMEOUT |
The keep-alive timeout for the server in seconds. | 5 |
No |
TZ |
Sets the timezone inside the container to ensure timestamps are correct. | UTC |
No |
Note on TZ: While the application does not directly use this variable, it is a standard in containerized environments to ensure that any timestamps (e.g., in logs) are correctly aligned with your local time.
When running with docker-compose, these variables are loaded from the .env file.
Installation (for Development)
For development purposes, you can install and run the server locally.
It is recommended to use a virtual environment.
# Install the package in editable mode with development dependencies
pip install -e ".[dev]"
Running the Development Server
The recommended way to run the development server is with uv:
# First, ensure uv is installed
pip install uv
# Run the server
uv run mcp dev src/immich_mcp/server.py
For Developers
- The MCP initialization handshake is documented in
docs/INITIALIZATION.md. - Functional tests that run against a real Immich instance are documented in
tests/functional/README.md.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.