io.github.ofershap/s3
编码与调试by ofershap
AWS S3 MCP 工具,可列出 buckets、浏览 objects、上传下载文件,并生成 presigned URLs。
什么是 io.github.ofershap/s3?
AWS S3 MCP 工具,可列出 buckets、浏览 objects、上传下载文件,并生成 presigned URLs。
README
mcp-server-s3
Manage AWS S3 buckets and objects from your AI assistant. Browse files, upload and download content, and generate presigned URLs.
npx mcp-server-s3
Works with Claude Desktop, Cursor, VS Code Copilot, and any MCP client. Uses your existing AWS credentials (
~/.aws/credentialsor environment variables).

<sub>Demo built with <a href="https://github.com/ofershap/remotion-readme-kit">remotion-readme-kit</a></sub>
Why
S3 is the most widely used cloud storage service, but managing it from the command line means remembering aws s3 ls, aws s3 cp, presigned URL syntax, and various flags. Google has an official MCP for GCS, Cloudflare has one for R2, but AWS S3 doesn't have a polished standalone MCP server on npm. This one lets you ask your assistant to list buckets, download a config file, upload content, or generate a temporary sharing link. It uses the standard AWS credential chain, so if your CLI already works, this works too.
Tools
| Tool | What it does |
|---|---|
list_buckets | List all S3 buckets in your AWS account. |
list_objects | List objects in a bucket, with optional prefix filter. |
get_object | Download and read an object's content as text. |
put_object | Upload text content to an S3 object. |
delete_object | Delete an object from a bucket. |
presigned_url | Generate a temporary presigned URL for an object. |
bucket_info | Check if a bucket exists and get basic info. |
Quick Start
Cursor
Add to .cursor/mcp.json:
{
"mcpServers": {
"s3": {
"command": "npx",
"args": ["mcp-server-s3"],
"env": {
"AWS_REGION": "us-east-1",
"AWS_ACCESS_KEY_ID": "your-access-key",
"AWS_SECRET_ACCESS_KEY": "your-secret-key"
}
}
}
}
Claude Desktop
Add to claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"s3": {
"command": "npx",
"args": ["mcp-server-s3"],
"env": {
"AWS_REGION": "us-east-1",
"AWS_ACCESS_KEY_ID": "your-access-key",
"AWS_SECRET_ACCESS_KEY": "your-secret-key"
}
}
}
}
VS Code
Configure the MCP server to run npx mcp-server-s3 with AWS_REGION, AWS_ACCESS_KEY_ID, and AWS_SECRET_ACCESS_KEY in the environment.
Authentication
The server uses the standard AWS credential chain:
- Environment variables:
AWS_ACCESS_KEY_ID,AWS_SECRET_ACCESS_KEY,AWS_REGION - Shared credentials file:
~/.aws/credentials - IAM roles: when running on EC2, ECS, Lambda, or similar
Set AWS_REGION (defaults to us-east-1) and make sure your credentials have the necessary S3 permissions: s3:ListBuckets, s3:ListBucket, s3:GetObject, s3:PutObject, s3:DeleteObject, s3:HeadBucket.
Example prompts
- "List all my S3 buckets"
- "Show me the files in my-bucket/uploads/"
- "Download the config.json from my-bucket"
- "Upload this content to my-bucket/notes.txt"
- "Generate a presigned URL for this file that expires in 1 hour"
Development
npm install
npm run typecheck
npm run build
npm test
npm run format
npm run lint
See also
More MCP servers and developer tools on my portfolio.
Author
<sub>README built with README Builder</sub>
License
MIT © 2026 Ofer Shapira
常见问题
io.github.ofershap/s3 是什么?
AWS S3 MCP 工具,可列出 buckets、浏览 objects、上传下载文件,并生成 presigned URLs。
相关 Skills
前端设计
by anthropics
面向组件、页面、海报和 Web 应用开发,按鲜明视觉方向生成可直接落地的前端代码与高质感 UI,适合做 landing page、Dashboard 或美化现有界面,避开千篇一律的 AI 审美。
✎ 想把页面做得既能上线又有设计感,就用前端设计:组件到整站都能产出,难得的是能避开千篇一律的 AI 味。
网页应用测试
by anthropics
用 Playwright 为本地 Web 应用编写自动化测试,支持启动开发服务器、校验前端交互、排查 UI 异常、抓取截图与浏览器日志,适合调试动态页面和回归验证。
✎ 借助 Playwright 一站式验证本地 Web 应用前端功能,调 UI 时还能同步查看日志和截图,定位问题更快。
网页构建器
by anthropics
面向复杂 claude.ai HTML artifact 开发,快速初始化 React + Tailwind CSS + shadcn/ui 项目并打包为单文件 HTML,适合需要状态管理、路由或多组件交互的页面。
✎ 在 claude.ai 里做复杂网页 Artifact 很省心,多组件、状态和路由都能顺手搭起来,React、Tailwind 与 shadcn/ui 组合效率高、成品也更精致。
相关 MCP Server
GitHub
编辑精选by GitHub
GitHub 是 MCP 官方参考服务器,让 Claude 直接读写你的代码仓库和 Issues。
✎ 这个参考服务器解决了开发者想让 AI 安全访问 GitHub 数据的问题,适合需要自动化代码审查或 Issue 管理的团队。但注意它只是参考实现,生产环境得自己加固安全。
Context7 文档查询
编辑精选by Context7
Context7 是实时拉取最新文档和代码示例的智能助手,让你告别过时资料。
✎ 它能解决开发者查找文档时信息滞后的问题,特别适合快速上手新库或跟进更新。不过,依赖外部源可能导致偶尔的数据延迟,建议结合官方文档使用。
by tldraw
tldraw 是让 AI 助手直接在无限画布上绘图和协作的 MCP 服务器。
✎ 这解决了 AI 只能输出文本、无法视觉化协作的痛点——想象让 Claude 帮你画流程图或白板讨论。最适合需要快速原型设计或头脑风暴的开发者。不过,目前它只是个基础连接器,你得自己搭建画布应用才能发挥全部潜力。