🔗 Official Repository
github.com/alexei-led/aws-mcp-serverAlways check the official repository for the latest setup instructions and license.
What is it?
A lightweight but powerful server that enables AI assistants to execute AWS CLI commands, use Unix pipes, and apply prompt templates for common AWS tasks in a — is a Model Context Protocol (MCP) server enabling AI applications like Claude and Cursor to securely access cloud platforms capabilities through the open protocol.
Why alexei-led/aws-mcp-server?
The AWS MCP Server enables Claude to interact with over 200 AWS services by wrapping the AWS CLI directly. Rather than using separate API wrappers, it uses two tools (`aws_cli_help` and `aws_cli_pipeline`) so Claude can look up command usage and run CLI pipelines under your local IAM permissions.
Common Use Cases
- Executing AWS CLI commands directly through Claude with output filtering using tools like jq or grep
- Fetching on-demand documentation for any AWS service command using aws_cli_help
- Managing AWS cloud infrastructure resources using Claude while enforcing existing IAM security policies
Quick Install (Claude Desktop)
{
"mcpServers": {
"aws-mcp-server": {
"command": "npx",
"args": ["-y", "alexei-led/aws-mcp-server"]
}
}
}Add to your Claude Desktop config file after installing requirements per the repo instructions.
Frequently Asked Questions
How does the AWS MCP Server communicate with AWS?
It wraps the AWS CLI installed on your machine, allowing Claude to execute commands via the `aws_cli_pipeline` tool.
How are security permissions controlled?
All actions performed by Claude are governed entirely by your locally configured AWS credentials and IAM policies.
What are the prerequisites to use this server?
You need the AWS CLI installed and configured with AWS credentials, plus the `uv` package manager to run `uvx aws-mcp`.