saveformedearai
MCP server for uploading, listing, and retrieving files on S3-compatible storage (AWS S3, DigitalOcean Spaces) with public/private access and temporary URLs.
README
<div align="center">
SaveForMeDearAI
A Model Context Protocol (MCP) server for managing files on S3 storage, supporting AWS S3 and DigitalOcean Spaces.
</div>
Features
- 🚀 Upload public and private files with metadata
- 📋 List files with descriptions and information
- 🔗 Immediate URL access - URLs returned directly in upload response
- 🌍 Global and local configuration for projects
- ⚡ Multi-provider support (AWS S3, DigitalOcean Spaces, S3-compatible)
- 🎯 Claude Code integration via MCP
Installation
Global Installation
npm install -g saveformedearai
Installation from Source
git clone https://github.com/bramato/saveForMeDearAi.git
cd saveForMeDearAi
npm install
npm run build
npm install -g .
Configuration
Quick Setup (2 steps)
- Install and configure:
npm install -g saveformedearai
saveformedearai setup
- Add to Claude MCP config:
{
"mcpServers": {
"saveformedearai": {
"command": "saveformedearai"
}
}
}
Available Commands
# Configure S3 drive (global)
saveformedearai setup
# Initialize local project
saveformedearai init
# Start MCP server (automatic when called by Claude)
saveformedearai
Configuration Structure
Global Configuration
Saved in ~/.saveformedearai/config.json:
{
"defaultDrive": "my-aws-drive",
"drives": {
"my-aws-drive": {
"endpoint": "https://s3.amazonaws.com",
"region": "us-east-1",
"accessKeyId": "YOUR_ACCESS_KEY",
"secretAccessKey": "YOUR_SECRET_KEY",
"bucketName": "my-bucket"
}
}
}
Local Configuration
Saved in .claude/saveformedearai.json:
{
"driveName": "my-project-drive",
"projectDirectory": "my-project",
"s3Config": {
"endpoint": "https://nyc3.digitaloceanspaces.com",
"region": "nyc3",
"accessKeyId": "YOUR_DO_KEY",
"secretAccessKey": "YOUR_DO_SECRET",
"bucketName": "my-space"
}
}
Available MCP Tools
1. save_public_file
Save a file as public and return the permanent URL.
{
"filePath": "/path/to/file.jpg",
"filename": "optional-custom-name.jpg", // optional
"description": "File description" // optional
}
Response:
{
"success": true,
"url": "https://bucket.endpoint.com/file.jpg",
"key": "file.jpg",
"urlType": "permanent",
"isPublic": true,
"message": "File uploaded successfully as public file. URL: https://bucket.endpoint.com/file.jpg",
"driveName": "my-drive"
}
2. save_private_file
Save a file as private.
{
"filePath": "/path/to/private-file.pdf",
"filename": "document.pdf",
"description": "Private document"
}
Response:
{
"success": true,
"key": "document.pdf",
"url": "https://presigned-url...",
"temporaryUrl": "https://presigned-url...",
"urlType": "temporary",
"expiresIn": 3600,
"expirationDate": "2024-01-15T11:30:00Z",
"message": "File uploaded successfully as private file. Temporary URL provided (expires in 1 hour).",
"driveName": "my-drive"
}
3. list_files
List all files with metadata.
{
"prefix": "images/" // optional, filter by prefix
}
Response:
{
"success": true,
"files": [
{
"filename": "image.jpg",
"description": "Sample photo",
"uploadDate": "2024-01-15T10:30:00Z",
"isPublic": true,
"size": 1024000,
"contentType": "image/jpeg",
"sizeFormatted": "1.02 MB"
}
],
"count": 1,
"driveName": "my-drive"
}
4. get_file_url
Get URL for a file (permanent for public, temporary for private).
{
"filename": "document.pdf",
"expiresIn": 3600 // optional, seconds (max 7 days)
}
Response for public file:
{
"success": true,
"url": "https://bucket.endpoint.com/document.pdf",
"urlType": "permanent",
"isPublic": true,
"filename": "document.pdf"
}
Response for private file:
{
"success": true,
"url": "https://presigned-url...",
"urlType": "temporary",
"isPublic": false,
"expiresIn": 3600,
"expirationDate": "2024-01-15T11:30:00Z"
}
Provider Support
AWS S3
Endpoint: https://s3.amazonaws.com
Force Path Style: false
DigitalOcean Spaces
Endpoint: https://[region].digitaloceanspaces.com
Force Path Style: false
S3-Compatible (Minio, etc.)
Endpoint: https://your-endpoint.com
Force Path Style: true (typically)
Development
# Clone repository
git clone https://github.com/bramato/saveForMeDearAi.git
cd saveForMeDearAi
# Install dependencies
npm install
# Build
npm run build
# Development with watch
npm run dev
# Test locally
npm start
Troubleshooting
Error "No configuration found"
Run saveformedearai setup to configure an S3 drive.
S3 connection error
Verify:
- Correct credentials
- Correct endpoint for provider
- Bucket exists and is accessible
- Adequate permissions (read/write for bucket)
File not found
Use list_files to verify file names in the bucket.
License
MIT
Contributing
Contributions are welcome! Please open an issue or pull request.
🎵 Support the Developer
Love coding with chill vibes? Support this project by listening to my developer album:
"Code Chill: Loops of Relaxation" 🎧
Perfect background music for your coding sessions
<div align="center">
</div>
Every stream helps support the development of free tools like this one! 🙏
</div>
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。