The AWS Infrastructure as Code (IaC) MCP Server is a new tool designed to enhance AWS infrastructure development by integrating AI assistance into workflows. It utilizes the Model Context Protocol (MCP) to let AI assistants like Kiro CLI and Claude access AWS CloudFormation and Cloud Development Kit (CDK) documentation, validate templates, and troubleshoot deployments securely on local machines. This server features nine specialized tools split into two categories: remote documentation search tools and local validation and troubleshooting tools. Remote tools include options for searching CDK documentation and CloudFormation resources, while local tools offer validation of CloudFormation templates and compliance checks using AWS Guard rules. For example, users can ask the AI to validate a CloudFormation template, and it will identify issues like missing encryption on EBS volumes. The server runs exclusively on local machines and uses existing AWS credentials, ensuring that sensitive data remains protected. Communication with AI assistants occurs through standard input/output without opening network ports, limiting exposure to security risks. Getting started with the IaC MCP Server requires Python 3.10 or later, the uv package manager, and configured AWS credentials. Users must set up their MCP client configuration, particularly for Kiro CLI. The server’s functionality hinges on minimal IAM permissions, primarily read-only access to CloudFormation and CloudTrail APIs for deployment troubleshooting. Best practices emphasize using documentation searches before coding, validating templates early, and leveraging CloudTrail for detailed troubleshooting information.