Photos Macos MCP
P

Photos Macos MCP

An MCP server developed based on Swift, providing AI assistants with read - only access to the macOS photo library. It realizes photo browsing, searching, and metadata query functions through the PhotoKit framework.
2.5 points
6.0K

What is PhotosMCP?

PhotosMCP is a bridge that connects AI assistants (such as Claude) with your macOS photo library. It allows AI assistants to access your photos and videos in read - only mode, helping you search and organize memories through natural language. For example, you can ask 'Find the photos I took in Paris last year' or 'Show all photos related to the beach'.

How to use PhotosMCP?

Just configure it once in Claude Desktop, and then you can query your photo library as if chatting with a friend. The AI assistant can help you find photos by location, date, content, or album, and even generate photo descriptions and memory summaries.

Use Scenarios

• Quickly find photos taken at a specific time or location • Organize travel photos and generate travel memoirs • Find photos of specific themes (such as food, pets, scenery) • Statistics information about the photo library (number of photos, time range, etc.) • Browse and manage photo albums

Main Features

Intelligent Photo Search
Supports searching for photos by date, location, and content keywords (such as 'beach', 'food', 'city'), and uses AI technology to identify photo content.
Geographical Location Search
Search for photos by place names (such as 'Paris', 'Tokyo') or latitude and longitude. Automatically convert place names to coordinates and search for photos taken nearby.
Album Management
Browse all albums (including smart albums), view album content and statistical information.
Photo Preview
Get photo thumbnails or full - size images, support base64 format output, making it convenient for AI assistants to view photo content.
Library Statistics Information
Get overall statistics of the photo library: number of photos, number of videos, time range, number of albums, etc.
Secure Read - Only Access
Only provides read - only permissions and will not modify, delete, or create any photos or albums, ensuring data security.
Advantages
Natural language interaction: Find photos by chatting, no need to browse manually
Intelligent recognition: AI automatically recognizes photo content (food, scenery, pets, etc.)
Privacy protection: Runs locally only, and photo data will not be uploaded to the cloud
Easy to use: Configure once and use permanently, no need for repeated operations
Cross - album search: Search all albums simultaneously, breaking album boundaries
Limitations
Only available for macOS: Requires macOS 13.0 or higher
Requires photo access permission: Authorization to access the photo library is required for the first use
Read - only function: Unable to edit, delete, or organize photos
Limited keyword recognition: Content recognition is based on pre - trained models and may not recognize all content
Geographical location search depends on the network: Converting place names to coordinates requires an Internet connection

How to Use

Installation and Building
Make sure you have installed Xcode 16+ and Swift 6.0+, and then build the project.
Configure Claude Desktop
Add the PhotosMCP server path to the Claude Desktop configuration file.
Add Configuration
Add the following content to the configuration file (replace with your actual path).
Authorize Photo Access
When using it for the first time, the system will prompt you to authorize photo access. Go to System Settings → Privacy & Security → Photos and make sure the Claude app has access permission.
Restart and Start Using
Restart Claude Desktop, and then you can start querying photos in natural language.

Usage Examples

Travel Memory Organization
You just came back from a trip to Japan and want to organize your travel photos and generate a travel summary.
Finding Specific Photos
You remember taking a photo of a delicious pizza but forget which album it's in.
Family Photo Organization
You want to organize your child's growth photos, categorize them by year and location.
Photo Library Analysis
You want to understand your photo - taking habits and the status of your photo library.

Frequently Asked Questions

Will PhotosMCP modify or delete my photos?
Will my photo data be uploaded to the cloud?
Why can't some photos be found by keywords?
Does it support searching for videos?
Do I need to keep an Internet connection all the time?
How to revoke photo access permission?
Does it support the iCloud photo library?
What is the search speed like?

Related Resources

Model Context Protocol Official Documentation
Understand the technical details and specifications of the MCP protocol.
Claude Desktop Download
Download the Claude Desktop application.
Apple PhotoKit Framework Documentation
Technical documentation of the underlying Apple Photos framework used by PhotosMCP.
Swift Programming Language
The programming language used by PhotosMCP.

Installation

Copy the following command to your Client for configuration
{
     "mcpServers": {
       "photos": {
         "command": "/Users/YOUR_USERNAME/Developer/photos-macos-mcp/.build/release/PhotosMCP",
         "args": []
       }
     }
   }
Note: Your key is sensitive information, do not share it with anyone.

Alternatives

A
Airweave
Airweave is an open - source context retrieval layer for AI agents and RAG systems. It connects and synchronizes data from various applications, tools, and databases, and provides relevant, real - time, multi - source contextual information to AI agents through a unified search interface.
Python
6.2K
5 points
V
Vestige
Vestige is an AI memory engine based on cognitive science. By implementing 29 neuroscience modules such as prediction error gating, FSRS - 6 spaced repetition, and memory dreaming, it provides long - term memory capabilities for AI. It includes a 3D visualization dashboard and 21 MCP tools, runs completely locally, and does not require the cloud.
Rust
5.0K
4.5 points
M
Moltbrain
MoltBrain is a long-term memory layer plugin designed for OpenClaw, MoltBook, and Claude Code, capable of automatically learning and recalling project context, providing intelligent search, observation recording, analysis statistics, and persistent storage functions.
TypeScript
5.5K
4.5 points
H
Haiku.rag
Haiku RAG is an intelligent retrieval - augmented generation system built on LanceDB, Pydantic AI, and Docling. It supports hybrid search, re - ranking, Q&A agents, multi - agent research processes, and provides local - first document processing and MCP server integration.
Python
10.4K
5 points
C
Cipher
Cipher is an open-source memory layer framework designed for programming AI agents. It integrates with various IDEs and AI coding assistants through the MCP protocol, providing core functions such as automatic memory generation, team memory sharing, and dual-system memory management.
TypeScript
0
5 points
V
Video Editing MCP
Video Editor MCP is a video editing server that provides video upload, search, generation, and editing functions, supporting operations through the LLM and Video Jungle platforms.
Python
16.1K
4 points
A
Apple Notes MCP
A server that provides local Apple Notes database access for the Claude desktop client, supporting reading and searching of note content.
Python
13.6K
4.3 points
M
MCP Server Weread
The WeRead MCP Server is a lightweight service that bridges WeRead data and AI clients, enabling in - depth interaction between reading notes and AI.
TypeScript
15.3K
4 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
34.6K
5 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
72.6K
4.3 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
20.5K
4.5 points
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
25.7K
4.3 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
63.8K
4.5 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
31.5K
5 points
G
Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
22.1K
4.5 points
M
Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
48.5K
4.8 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
© 2026AIBase