AWS Support MCP Server

AWS Support MCP Server

A Model Context Protocol (MCP) server implementation for interacting with the AWS Support API. This server enables AI assistants to create and manage AWS support cases programmatically.

Features

• Create and manage AWS support cases
• Retrieve case information and full communication history
• Add communications to existing cases (with attachment support)
• Resolve support cases
• Upload and download attachments with double-encoding protection
• Discover valid service codes, category codes, severity levels, and languages before creating a case
• Browse available case creation options per service

Available Tools

Tool	Description
create_support_case	Create a new support case
describe_support_cases	List/search existing cases
describe_communications	Get full communication history for a case
add_communication_to_case	Reply to a case (with optional attachments)
resolve_support_case	Close a case
describe_services	List AWS services and category codes
describe_severity_levels	List severity levels
describe_create_case_options	Get valid categories/severities for a service
describe_supported_languages	List supported languages
add_attachments_to_set	Upload files for attachment to cases
describe_attachment	Download an attachment by ID

Requirements

• Python 3.7+
• AWS credentials with Support API access
• Business, Enterprise On-Ramp, or Enterprise Support plan

Prerequisites

1. Install uv from Astral or the GitHub README
2. Install Python using uv python install 3.10

Installation

Kiro	Cursor	VS Code

Configure the MCP server in your MCP client configuration (e.g., for Kiro, edit ~/.kiro/settings/mcp.json):

{
   "mcpServers": {
      "awslabs_support_mcp_server": {
         "command": "uvx",
         "args": [
            "-m", "awslabs.aws-support-mcp-server@latest",
            "--debug",
            "--log-file",
            "./logs/mcp_support_server.log"
         ],
         "env": {
            "AWS_PROFILE": "your-aws-profile"
         }
      }
   }
}

Alternatively:

uv pip install -e .
uv run awslabs/aws_support_mcp_server/server.py

{
   "mcpServers": {
      "awslabs_support_mcp_server": {
         "command": "path-to-python",
         "args": [
            "-m",
            "awslabs.aws_support_mcp_server.server",
            "--debug",
            "--log-file",
            "./logs/mcp_support_server.log"
         ],
         "env": {
            "AWS_PROFILE": "manual_enterprise"
         }
      }
   }
}

Windows Installation

For Windows users, the MCP server configuration format is slightly different:

{
  "mcpServers": {
    "awslabs.aws-support-mcp-server": {
      "disabled": false,
      "timeout": 60,
      "type": "stdio",
      "command": "uv",
      "args": [
        "tool",
        "run",
        "--from",
        "awslabs.aws-support-mcp-server@latest",
        "awslabs.aws-support-mcp-server.exe"
      ],
      "env": {
        "FASTMCP_LOG_LEVEL": "ERROR",
        "AWS_PROFILE": "your-aws-profile",
        "AWS_REGION": "us-east-1"
      }
    }
  }
}

Usage

Start the server:

python -m awslabs.aws_support_mcp_server.server [options]

Options:

• --port PORT: Port to run the server on (default: 8888)
• --debug: Enable debug logging
• --log-file: Where to save the log file

Configuration

The server can be configured using environment variables:

• AWS_REGION: AWS region (default: us-east-1)
• AWS_PROFILE: AWS credentials profile name

Documentation

For detailed documentation on available tools and resources, see the API Documentation.

License

Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.

Licensed under the Apache License, Version 2.0 (the "License").