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>
π¬ Demo
See it in action! Here's how easy it is to spin up a full-blown EC2 setup β VPC, subnets, security groups, this works β 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>
β¨ 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 π
π 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)
βοΈ Developer Setup
1. Clone the repo
git clone https://github.com/lokeswaran-aj/aws-mcp.git
cd aws-mcp
βοΈCurrently, the server reads credentials from MCP configuration headers. In future versions, we'll support AWS Role ARN.
2. Install dependencies
pnpm install
π‘ Make sure you have
pnpminstalled globally. If not:npm install -g pnpm
3. Run the dev server
pnpm dev
π³ 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
π‘ AWS credentials are still passed via HTTP headers (same as development setup). No container configuration needed.
π§ͺ 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"
}
}
}
}
βοΈ 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
π Project Structure
.
βββ src/
β βββ server.ts # AWS MCP server setup - Entry point
β βββ aws-clients.ts # AWS SDK client setup
β βββ config/ # App configuration
β βββ tools/ # Tools definitions
β β βββ rds/ # RDS operations
β β βββ s3/ # S3 operations
β β βββ ec2/ # EC2 operations
β β βββ vpc/ # VPC operations
β β βββ subnet/ # Subnet operations
β β βββ internet-gateway/ # Internet Gateway operations
β β βββ route-table/ # Route Table operations
β β βββ security-group/ # Security Group operations
β β βββ key-pair/ # Key Pair operations
β β βββ instance-tag/ # Instance Tag operations
β β βββ ami/ # AMI operations
β βββ schema/ # Tool input schemas
β βββ types/ # TypeScript definitions
β βββ utils/ # Helper functions
βββ package.json # Dependencies and scripts
βββ README.md # This file
π 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
π€ 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 π
π License
MIT β do what you want, just give credit where it's due. βοΈ
β‘ Powered by
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
E2B
Using MCP to run code via e2b.