AWS Model Context Protocol (MCP) Server

Bridges MCP-enabled AI assistants with the AWS CLI to retrieve help, execute commands, and format outputs for AI workflows.

python

GitHub Stars

python

Language

5 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "mcp-mirror-alexei-led_aws-mcp-server": {
      "command": "python",
      "args": [
        "-m",
        "aws_mcp_server"
      ],
      "env": {
        "AWS_REGION": "us-east-1",
        "AWS_PROFILE": "default",
        "AWS_MCP_TIMEOUT": "300",
        "AWS_MCP_TRANSPORT": "stdio",
        "AWS_MCP_MAX_OUTPUT": "100000",
        "AWS_MCP_SECURITY_MODE": "strict"
      }
    }
  }
}

The AWS MCP Server lets MCP-aware AI assistants execute AWS CLI commands and retrieve AWS CLI help, providing a bridge between conversational agents and your AWS environment. It enables you to explore AWS documentation, run commands, and pipe outputs for tailored AI insights while preserving control through containerized or local execution.

How to use

You interact with the AWS MCP Server through an MCP client by calling AWS CLI commands and receiving results that are formatted for easy consumption by an assistant. Start by choosing a deployment method, then connect your MCP client to the server. You can retrieve command help, run AWS CLI operations, and apply Unix pipes to filter or transform results. When you use the server, it leverages your existing AWS credentials and profile configurations to perform actions in your AWS account.

How to install

Prerequisites: you need Docker or Python 3.13+ installed, and AWS CLI configured with credentials.

Option A: Run with Docker (recommended)

Ensure Docker is installed on your machine.
Obtain and run the MCP server container using Docker Compose or a direct run command. The example below demonstrates running the server via a Docker command with your AWS credentials mounted read-only.
If you prefer a quick container setup, the following run command mounts your AWS credentials read-only and starts the server image.

# Example Docker run (adjust YOUR_USER_NAME and path as needed)
docker run -i --rm \
  -v /Users/YOUR_USER_NAME/.aws:/home/appuser/.aws:ro \
  ghcr.io/alexei-led/aws-mcp-server:latest

Additional installation notes

Option B: Run with Python (local development)

Clone the project repository and navigate into it.
Create a Python virtual environment and activate it.
Install in development mode and start the server.

# Clone repository
git clone https://github.com/alexei-led/aws-mcp-server.git
cd aws-mcp-server

# Set up virtual environment
python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

# Install in development mode
pip install -e .

# Run the server
python -m aws_mcp_server

Available tools

command_documentation

Provide detailed AWS CLI command help and syntax for requested AWS services and commands.

command_execution

Execute AWS CLI commands and return results in a formatted, AI-friendly manner, with support for Unix pipes.

pipe_support

Support Unix pipes to filter and transform AWS CLI output for easier AI consumption.

resources_context

Access to AWS resources context such as profiles, regions, account information, and environment details within MCP.

prompt_templates

Pre-defined prompt templates for common AWS tasks to streamline AI-assisted workflows.

docker_integration

Containerized deployment support to isolate and simplify secure usage.

aws_auth

Leverage existing AWS credentials provided to the server to perform actions.

Built by

VeilStrat

AI signals for GTM teams