AWS Model Context Protocol (MCP) Server

Source

A lightweight service that enables AI assistants to execute AWS CLI commands (in safe containerized environment) through the Model Context Protocol (MCP). Bridges Claude, Cursor, and other MCP-aware AI tools with AWS CLI for enhanced cloud infrastructure management.

Catalog onlyCatalog onlyDocker

Overview

AWS Model Context Protocol (MCP) Server is a lightweight service that enables AI assistants to execute AWS CLI commands through the Model Context Protocol (MCP).

To use the AWS MCP Server, you can deploy it using Docker or Python. After starting the server, MCP-aware AI assistants can connect to it and use tools to retrieve AWS CLI documentation and execute commands.

Fully implements the Model Context Protocol (MCP) - Provides detailed help information for AWS CLI commands - Executes AWS CLI commands and returns human-readable results - Supports Docker for easy deployment with multi-architecture support - Utilizes existing AWS credentials on the host machine

Enabling AI assistants to interact with AWS services via CLI commands.
Providing documentation and command execution capabilities for AWS CLI.
Integrating with applications like Claude Desktop for enhanced AWS management.

Add to your AI client

Use these steps to connect AWS Model Context Protocol (MCP) Server in Cursor, Claude, VS Code, and other MCP-compatible apps. The same JSON appears in the Use with menu above for one-click copy.

Cursor

Add this to your .cursor/mcp.json file in your project root, then restart Cursor.

.cursor/mcp.json

{
  "mcpServers": {
    "aws-mcp-server-alexei-led": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-v",
        "/Users/YOUR_USER_NAME/.aws:/home/appuser/.aws:ro",
        "ghcr.io/alexei-led/aws-mcp-server:latest"
      ]
    }
  }
}

Claude Desktop

Add this server entry to the mcpServers object in your Claude Desktop config, then restart the app.

~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)

{
  "mcpServers": {
    "aws-mcp-server-alexei-led": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-v",
        "/Users/YOUR_USER_NAME/.aws:/home/appuser/.aws:ro",
        "ghcr.io/alexei-led/aws-mcp-server:latest"
      ]
    }
  }
}

Claude Code

Add this to your project's .mcp.json file. Claude Code will detect it automatically.

.mcp.json (project root)

{
  "mcpServers": {
    "aws-mcp-server-alexei-led": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-v",
        "/Users/YOUR_USER_NAME/.aws:/home/appuser/.aws:ro",
        "ghcr.io/alexei-led/aws-mcp-server:latest"
      ]
    }
  }
}

VS Code (Copilot)

Add this to your .vscode/mcp.json file. Requires the GitHub Copilot extension with MCP support enabled.

.vscode/mcp.json

{
  "servers": {
    "aws-mcp-server-alexei-led": {
      "type": "stdio",
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-v",
        "/Users/YOUR_USER_NAME/.aws:/home/appuser/.aws:ro",
        "ghcr.io/alexei-led/aws-mcp-server:latest"
      ]
    }
  }
}

Windsurf

Add this to your Windsurf MCP config file, then restart Windsurf.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "aws-mcp-server-alexei-led": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-v",
        "/Users/YOUR_USER_NAME/.aws:/home/appuser/.aws:ro",
        "ghcr.io/alexei-led/aws-mcp-server:latest"
      ]
    }
  }
}

Cline

Open Cline settings, navigate to MCP Servers, and add this server configuration.

Cline MCP Settings (via UI)

{
  "mcpServers": {
    "aws-mcp-server-alexei-led": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-v",
        "/Users/YOUR_USER_NAME/.aws:/home/appuser/.aws:ro",
        "ghcr.io/alexei-led/aws-mcp-server:latest"
      ]
    }
  }
}

FAQ

Can I run AWS MCP Server without Docker?

Yes, you can run it using Python, but Docker is recommended for easier setup.

What are the requirements for using AWS MCP Server?

You need Docker or Python 3.13+, AWS CLI installed, and AWS credentials configured.

How does AWS MCP Server handle security?

It uses AWS credentials from the host machine, validates commands before execution, and has timeout limits for commands.

Developer tools