AWS MCP Server
Enables management and provisioning of AWS resources like EC2, S3, and RDS using natural language prompts through the Model Context Protocol. It allows users to automate complex infrastructure tasks, such as setting up VPCs and security groups, via a chat interface.
README
<div align="center"> <img src="assets/banner.svg" width="1200" alt="demo"/> </div>
🎬 Demo
See it in action! Here's how easy it is to spin up a full-blown EC2 setup — VPC, subnets, security groups, this works — all through natural language prompts to an AI Model Context Protocol (MCP) server.
<div align="center" style="margin-top:20px;margin-bottom:20px;"> <img src="assets/demo.gif" width="1200" alt="demo"/> </div>
✨ Features
Currently supports
- RDS
- S3
- EC2
- VPC
- Subnet
- Internet Gateway
- Route Table
- Security Group
- Key Pair
- Instance Tag
- AMI
More AWS services (like Lambda, API Gateway, etc.) coming soon! Contributions welcome 🚀
📋 Prerequisites
For Development:
- Node.js >= 18.0.0
- pnpm >= 10.0.0
For Docker Deployment:
- Docker and Docker Compose
For Both:
- AWS Account with AWS credentials (Access Key ID and Secret Access Key)
⚙️ Developer Setup
1. Clone the repo
git clone https://github.com/lokeswaran-aj/aws-mcp.git
cd aws-mcp
❗️Currently, the server reads credentials from MCP configuration headers. In future versions, we'll support AWS Role ARN.
2. Install dependencies
pnpm install
💡 Make sure you have
pnpminstalled globally. If not:npm install -g pnpm
3. Run the dev server
pnpm dev
🐳 Docker Deployment
Quick Start with Docker
Option 1: Using Docker Compose (Recommended)
docker-compose up -d
Option 2: Using Docker directly
# Build the image
docker build -t aws-mcp .
# Run with port mapping
docker run -d --name aws-mcp-server -p 8080:8080 aws-mcp
The server will be available at:
- MCP HTTP Stream:
http://localhost:8080/mcp - MCP SSE:
http://localhost:8080/sse
Managing Docker Containers
# View logs
docker-compose logs -f
# Stop container
docker-compose down
# Rebuild and restart
docker-compose build --no-cache && docker-compose up -d
# Stop aws-mcp-server and remove container
docker stop aws-mcp-server && docker rm aws-mcp-server
💡 AWS credentials are still passed via HTTP headers (same as development setup). No container configuration needed.
🧪 Example: Cursor Configuration
To use this server with Cursor, add the following to your ~/.cursor/mcp.json:
{
"mcpServers": {
"aws": {
"serverUrl": "http://localhost:8080/mcp",
"headers": {
"AWS_ACCESS_KEY_ID": "YOUR_AWS_ACCESS_KEY_ID",
"AWS_SECRET_ACCESS_KEY": "YOUR_AWS_SECRET_ACCESS_KEY",
"AWS_SESSION_TOKEN": "YOUR_AWS_SESSION_TOKEN"
}
}
}
}
❗️ Use
http://localhost:8080/mcpif your client supports HTTP streamable(For eg: Cursor). Usehttp://localhost:8080/sseif your client supports only SSE(For eg: Windsurf).
MCP HTTP streamable endpoint: http://localhost:8080/mcp
MCP SSE endpoint: http://localhost:8080/sse
📁 Project Structure
.
├── src/
│ ├── server.ts # AWS MCP server setup - Entry point
│ ├── aws-clients.ts # AWS SDK client setup
│ ├── config/ # App configuration
│ ├── tools/ # Tools definitions
│ │ ├── rds/ # RDS operations
│ │ ├── s3/ # S3 operations
│ │ ├── ec2/ # EC2 operations
│ │ ├── vpc/ # VPC operations
│ │ ├── subnet/ # Subnet operations
│ │ ├── internet-gateway/ # Internet Gateway operations
│ │ ├── route-table/ # Route Table operations
│ │ ├── security-group/ # Security Group operations
│ │ ├── key-pair/ # Key Pair operations
│ │ ├── instance-tag/ # Instance Tag operations
│ │ ├── ami/ # AMI operations
│ ├── schema/ # Tool input schemas
│ ├── types/ # TypeScript definitions
│ └── utils/ # Helper functions
├── package.json # Dependencies and scripts
└── README.md # This file
📌 Roadmap
- [x] Support RDS (Create, List, Update, Delete)
- [x] Add S3 tools
- [x] Add Network tools
- [x] Add EC2 tools
- [ ] Add Lambda tools
- [ ] Add API Gateway tools
- [ ] Add IAM tools
- [ ] Add ECS tools
🤝 Contributing
Want to help make AWS infra chat-native? Pull requests, feedback, and feature suggestions are welcome!
- Clone and fork the repo
- Create your feature branch (
git checkout -b feat/add-ec2) - Commit and push
- Open a PR 🙌
📄 License
MIT — do what you want, just give credit where it's due. ✌️
⚡ Powered by
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。