What is AWS Core?

AWS Core is a foundational AWS MCP server designed to provide prompt understanding and server management capabilities. It acts as a central hub for integrating various AWS MCP servers into workflows.

How to use AWS Core?

1. Installation: Install AWS Core via Python 3.12+ and dependencies (uv, AWS credentials configured with Bedrock access, Node.js for UVX support).
2. Configuration: Add the server to your MCP client (e.g., Amazon Q Developer CLI) by editing the configuration file (~/.aws/amazonq/mcp.json). Alternatively, run it via Docker after building the image.
3. Usage: Interact with the server through the MCP interface to plan and orchestrate AWS solutions based on given prompts.

Key features of AWS Core?

• Prompt Understanding and Translation: Guides users in translating prompts into actionable AWS service configurations.
• Tool Orchestration: Coordinates various MCP servers (e.g., cdk-mcp-server, bedrock-kb-retrieval-mcp-server) to streamline workflows.
• Dual Deployment Options: Supports both direct installation (via uvx) and Docker containerization.

Use cases of AWS Core?

1. Building Custom AWS Solutions: Helps users design AWS-driven solutions by breaking down high-level prompts into structured workflows.
2. Customizable Server Integration: Provides a foundation for integrating specialized MCP servers (e.g., cost analysis or diagram tools).
3. Streamlined Development: Simplifies complex actions (e.g., using Bedrock KB for retrieval tasks) by offering preconfigured prompts.

FAQ about AWS Core?

• What are the system requirements?

Requires Python 3.12+, uv, AWS credentials with Bedrock access, and Node.js (for UVX). Docker is supported for containerized deployment.

• How does AWS Core differ from individual MCP servers?

Unlike specialized servers, AWS Core serves as a unifying layer, enabling coordinated use of tools like diagram generators or cost analysis while abstracting implementation details.

• Can I extend AWS Core with custom servers?

Yes! Users can add compatible MCP servers to their configuration file to expand functionality (e.g., add a new analysis server).

Core MCP Server

MCP server that provides a starting point for using the following awslabs MCP servers

• awslabs.cdk-mcp-server
• awslabs.bedrock-kb-retrieval-mcp-server
• awslabs.nova-canvas-mcp-server
• awslabs.cost-analysis-mcp-server
• awslabs.aws-documentation-mcp-server
• awslabs.aws-diagram-mcp-server

Features

Planning and orchestration

• Provides tool for prompt understanding and translation to AWS services

Prerequisites

• Python 3.12 or higher
• uv - Fast Python package installer and resolver
• AWS credentials configured with Bedrock access
• Node.js (for UVX installation support)

Installation

Configure the MCP server in your MCP client configuration (e.g., for Amazon Q Developer CLI, edit ~/.aws/amazonq/mcp.json):

{
  "mcpServers": {
    "awslabs.core-mcp-server": {
      "command": "uvx",
      "args": [
        "awslabs.core-mcp-server@latest"
      ],
      "env": {
        "FASTMCP_LOG_LEVEL": "ERROR"
      },
      "autoApprove": [],
      "disabled": false
    }
  }
}

or docker after a successful docker build -t awslabs/core-mcp-server .:

  {
    "mcpServers": {
      "awslabs.core-mcp-server": {
        "command": "docker",
        "args": [
          "run",
          "--rm",
          "--interactive",
          "--env",
          "FASTMCP_LOG_LEVEL=ERROR",
          "awslabs/core-mcp-server:latest"
        ],
        "env": {},
        "disabled": false,
        "autoApprove": []
      }
    }
  }

Tools and Resources

The server exposes the following tools through the MCP interface:

• prompt_understanding - Helps to provide guidance and planning support when building AWS Solutions for the given prompt