Photo Organizer

io.github.ExpertVagabond由 GitHub 账号 ExpertVagabond 发布v1.0.0更新于 Oct 26, 2026

AI-powered organization for Google Photos and Drive - auto-organize, find duplicates, create albums

已验证STDIO仅桌面文件与存储媒体与设计

概览

AI 生成的概览

本地 MCP 服务器,让助手分析、整理、归档并去重 Google 相册与 Google 云端硬盘内容。

可以做什么
  • 分析 Google 相册图库,获取统计信息并找出疑似重复照片
  • 按年份或月份创建相册
  • 分析 Google 云端硬盘,获取文件统计与存储概况
  • 按类型将云端硬盘文件归类到文件夹,并归档旧文件
  • 查找并删除完全重复的云端硬盘文件
  • 所有操作默认演练模式,需显式执行才会真正改动
适用场景
适合希望让助手清理 Google 相册或云端硬盘的场景:查看图库统计、按时间整理相册、把文件分类到文件夹、归档旧文件或清理重复文件。
运行要求
以 npm 包 photo-organizer-mcp 通过 stdio 在本机运行,仅支持桌面端。需要启用 Google Photos Library API 与 Google Drive API 的 Google Cloud OAuth 2.0 凭据及凭据文件。需设置环境变量 PHOTO_SCRIPTS_PATH,指向包含 Python 整理脚本的目录。
安装前请注意
需要授予可访问相册与云端硬盘数据的 Google Cloud OAuth 凭据。去重会删除文件,整理与归档会移动文件,建议保持默认演练模式并先查看报告,再设置 execute 为 true。README 提到付费 Pro 与 Enterprise 版本及每月操作次数限制。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Photo Organizer,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Desktop only,通过 STDIO。 STDIO 服务会启动本地进程,因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照 仓库 中的启动说明。

README

Photo Organizer MCP Server

AI-powered organization for Google Photos and Google Drive.

This MCP server enables AI agents like Claude to automatically organize your Google Photos and Drive files. Perfect for decluttering cloud storage, finding duplicates, and maintaining organized photo albums.

Features

Google Photos

  • 📊 Analyze Library: Get statistics and insights about your photo collection
  • 🔍 Find Duplicates: Identify potential duplicate photos
  • 📅 Auto-Organize: Create albums by year or month
  • 📈 Reports: Generate detailed organization reports

Google Drive

  • 📂 Auto-Organize: Sort files into folders by type (Documents, Images, Videos, etc.)
  • 🗄️ Archive Old Files: Move old files to Archive folder
  • 🔄 Deduplicate: Find and remove exact duplicate files
  • 📊 Analytics: Get file statistics and storage insights

Installation

bash
# Install from NPMnpm install -g photo-organizer-mcp
# Or clone and buildgit clone https://github.com/ExpertVagabond/photo-organizer-mcpcd photo-organizer-mcpnpm installnpm run build

Setup

1. Google Cloud Credentials

You need Google Cloud credentials to access Photos and Drive APIs:

  1. Go to Google Cloud Console
  2. Create a new project
  3. Enable Google Photos Library API and Google Drive API
  4. Create OAuth 2.0 credentials
  5. Download credentials.json

2. Python Scripts

This MCP server wraps existing Python organizer scripts. Set the path:

bash
export PHOTO_SCRIPTS_PATH="/path/to/drive-photos-organizer"

Or add to .env:

PHOTO_SCRIPTS_PATH=/Users/yourname/drive-photos-organizer

3. Configure Claude Desktop

Add to your claude_desktop_config.json:

json
{  "mcpServers": {    "photo-organizer": {      "command": "photo-organizer-mcp",      "env": {        "PHOTO_SCRIPTS_PATH": "/path/to/drive-photos-organizer"      }    }  }}

Usage Examples

With Claude

"Analyze my Google Photos and find duplicates"

Claude will use the analyze_photos tool to scan your library

"Organize my photos into albums by year"

Claude will create year-based albums (dry run first, then execute)

"Clean up my Google Drive by organizing files into folders"

Claude will sort files by type into organized folders

"Archive all Drive files older than 2 years"

Claude will move old files to an Archive folder

"Find and remove duplicate files from my Drive"

Claude will identify and remove exact duplicates

Available Tools

Photo Tools

  1. analyze_photos - Get photo library statistics

    json
    {  "findDuplicates": true}
  2. organize_photos_by_date - Create date-based albums

    json
    {  "grouping": "year",  // or "month"  "execute": false     // true to actually create albums}

Drive Tools

  1. analyze_drive - Get Drive statistics

  2. organize_drive - Sort files into folders

    json
    {  "execute": false  // true to actually organize}
  3. archive_old_files - Move old files to Archive

    json
    {  "days": 730,      // Archive files older than this  "execute": false}
  4. deduplicate_drive - Remove duplicate files

    json
    {  "execute": false  // true to actually delete}

Safety Features

  • Dry Run by Default: All operations default to dry run mode
  • Explicit Execution: Must set execute: true to make changes
  • Detailed Reports: See exactly what will happen before executing
  • Non-Destructive: Organizes and archives, doesn't delete (except deduplication)

Monetization (Pro Version)

Upgrade for advanced features:

Free Tier

  • 50 operations per month
  • Basic organization
  • Manual execution required

Pro ($10/month)

  • Unlimited operations
  • Scheduled auto-organization
  • Advanced duplicate detection
  • Priority support

Enterprise ($50/month)

  • White-label branding
  • Team management
  • Custom rules engine
  • API access

Technical Details

  • Built with TypeScript and Model Context Protocol SDK
  • Wraps Python scripts for Google API integration
  • Async operation with progress reporting
  • Handles large libraries (10,000+ photos)

Contributing

Contributions welcome! Please open issues or PRs on GitHub.

License

MIT License - see LICENSE file

Author

ExpertVagabond - https://github.com/ExpertVagabond


Need help? Contact: [email protected]

来源:README.md,提交 53d7bec

工具

0
SourceWeft 尚未在沙箱中启动过该软件包,因此其工具未知。

版本历史

1
  1. v1.0.0最新Sep 16, 2026

评分

已满足适用检查项的 50%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通25 分

    请保持端点能够响应 MCP 握手;SourceWeft 每 30 天探测一次。

  • 已声明认证方式10 分

    请在注册中心条目中声明凭据请求头,或保持端点能够响应探测,以便判定其认证方式。

  • 已列出工具15 分

    请让服务器在无凭据时响应 tools/list,或发布可在沙箱中无凭据启动的软件包。

  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分