Description

This AWS Labs MCP server collection provides comprehensive integration with AWS services through multiple specialized servers including Bedrock Knowledge Bases, Nova Canvas image generation, Step Functions, Lambda, IAM, Cost Explorer, and many others. The implementation includes sample applications demonstrating real-world usage patterns, such as a Streamlit-based chatbot that integrates with Bedrock Knowledge Bases for RAG workflows and an image generator leveraging Nova Canvas with prompt improvement capabilities. Built with Python and FastAPI, the servers use the langchain-mcp-adapters for seamless integration and include extensive documentation, testing frameworks, and deployment guides, making it valuable for developers building AI applications that need deep AWS service integration for enterprise workflows, cost analysis, infrastructure management, and generative AI use cases.

Installation

git clone https://github.com/awslabs/mcp

Claude Desktop Configuration

Add this configuration to your Claude Desktop config file to enable this MCP server:

Config file location: ~/Library/Application Support/Claude/claude_desktop_config.json

Config file location: %APPDATA%\Claude\claude_desktop_config.json

Config file location: ~/.config/Claude/claude_desktop_config.json

claude_desktop_config.json

{
  "mcpServers": {
    "aws-labs": {
      "command": "node",
      "args": [
        "path/to/server.js"
      ]
    }
  }
}