Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@AWS MCP Serverlist my running EC2 instances and their status"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
AWS MCP Server
A Model Context Protocol (MCP) server that provides tools to interact with AWS services through Claude Desktop.
Features
S3: List buckets, list objects
EC2: Describe instances, security groups, VPCs
RDS: Describe database instances
Cost Explorer: Get cost and usage reports
CloudWatch: Retrieve metric statistics
Generic AWS SDK: Access any AWS operation via
aws_sdk_wrapperVector Store: Optional document ingestion and search capabilities
Quick Start
Prerequisites
Python 3.12+
AWS credentials configured (
~/.aws/credentials)Claude Desktop installed
Installation
Install the package:
pip install aws-mcp-serverConfigure Claude Desktop: Add to your
claude_desktop_config.json:{ "mcpServers": { "aws-mcp-server": { "command": "aws-mcp-server" } } }Configure AWS credentials:
aws configure # OR manually edit ~/.aws/credentials:[default] aws_access_key_id = YOUR_ACCESS_KEY aws_secret_access_key = YOUR_SECRET_KEY region = us-east-1
Development
Local Development Setup
Configuration Options
Set environment variables for customization:
Documentation
Deployment Guide - Production deployment with AWS App Runner
Vector Store Guide - Document ingestion and search setup
Workflow Guide - Development workflows and patterns
License
MIT License - see LICENSE file for details.