home / mcp / aws advisor mcp server

AWS Advisor MCP Server

My Dev MCP Server

Installation

Add the following to your MCP client configuration file.

Configuration

{
  "mcpServers": {
    "antonioschaffert-my-dev-mcp": {
      "command": "uv",
      "args": [
        "--directory",
        "/Users/antonioschaffert/workspace/tony/my-dev-mcp",
        "run",
        "python",
        "src/aws_advisor_server.py"
      ]
    }
  }
}

You run an MCP server that suggests AWS services based on your use case descriptions and lets you browse services by category. It provides practical planning guidance, helping you pick the most suitable AWS options quickly.

How to use

After you configure the MCP client, you can access two core capabilities. First, use suggest_aws_service to get AWS service recommendations by describing your use case. Second, use list_aws_categories to browse AWS services organized by category (such as Compute, Storage, Database, Networking, Analytics, ML/AI, Security, Messaging, and Monitoring). These tools enable you to plan infrastructure and find appropriate AWS offerings without leaving your MCP environment.

How to install

Prerequisites you need before installing: Python 3.10 or newer and access to the MCP tooling (uv). Install the MCP runtime tool if you do not already have it.

Additional sections

Install and run steps in order to start using the AWS Advisor MCP Server:

Configuration and usage notes

The MCP server runs as a stdio server using the MCP runtime to execute the Python script that provides AWS recommendations. You connect to it from your MCP client (for example, Cursor) using the following configuration and runtime command.

Available tools

suggest_aws_service

Input: use_case (string) - Description of what you want to build. Returns: Recommended AWS services with explanations.

list_aws_categories

No input required. Returns: All AWS service categories and their services.