awslabs/mcp: Enhance AI Assistants with AWS Model Context Protocol Servers

Introduction

AWS MCP Servers, found in the awslabs/mcp repository, are a collection of specialized tools built to extend the capabilities of AI applications within the AWS ecosystem. They leverage the Model Context Protocol (MCP), an open standard that facilitates robust integration between LLM applications and external data sources or tools. Whether you are developing an AI-powered IDE, enhancing a chatbot, or creating custom AI workflows, MCP provides a standardized way to connect LLMs with the essential context they need.

By using this protocol, AWS MCP Servers grant AI applications access to up-to-date AWS documentation, contextual guidance, and adherence to best practices. This client-server architecture transforms AWS capabilities into an intelligent extension of your development environment or AI application, enabling enhanced cloud-native development, infrastructure management, and overall development workflows, making AI-assisted cloud computing more accessible and efficient.

Why Use AWS MCP Servers?

MCP servers significantly enhance the capabilities of foundation models (FMs) in several key areas:

Improved Output Quality: By injecting relevant, up-to-date information directly into the model's context, MCP servers drastically improve responses for specialized domains like AWS services. This approach minimizes hallucinations, delivers more accurate technical details, enables precise code generation, and ensures recommendations align with current AWS best practices and service capabilities.
Access to Latest Documentation: Foundation models may not always have knowledge of the most recent releases, APIs, or SDKs. MCP servers bridge this gap by fetching the latest documentation, ensuring your AI assistant always operates with the most current AWS capabilities.
Workflow Automation: MCP servers convert common workflows into tools that foundation models can directly utilize. For tasks involving CDK, Terraform, or other AWS-specific workflows, these tools empower AI assistants to perform complex operations with greater accuracy and efficiency.
Specialized Domain Knowledge: These servers provide deep, contextual knowledge about AWS services that might not be fully represented in foundation models' training data, leading to more accurate and helpful responses for cloud development tasks.

Installation

To get started with AWS MCP Servers, you'll generally follow these steps:

Install uv from Astral.
Install Python using uv python install 3.10.
Configure your AWS credentials with access to the required services.
Add the desired server to your MCP client configuration.

For example, a basic configuration for Kiro MCP settings on macOS/Linux (~/.kiro/settings/mcp.json) would look like this:

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

Docker images for each MCP server are also published to the public AWS ECR registry, allowing for containerized deployments. Refer to individual server READMEs for specific requirements and detailed configuration options.

Examples

AWS MCP Servers offer a wide range of functionalities for various use cases:

AWS Documentation MCP Server: Helps your AI assistant research and generate up-to-date code for any AWS service, such as Amazon Bedrock Inline agents.
AWS IaC MCP Server (or Terraform/CDK MCP Servers): Enables your AI assistant to create infrastructure-as-code implementations that utilize the latest APIs and adhere to AWS best practices.
AWS Pricing MCP Server: Allows you to inquire about estimated monthly costs for a CDK project before deployment or understand potential AWS service expenses for infrastructure designs, receiving detailed cost estimations and budget planning insights.
Amazon DynamoDB MCP Server: Provides expert design guidance and data modeling assistance for DynamoDB.
Valkey MCP Server: Facilitates natural language interaction with Valkey data stores, enabling AI assistants to efficiently manage data operations through a simple conversational interface.