AWS announces a preview of the AWS MCP Server

Today, AWS announces the AWS MCP Server, a managed remote Model Context Protocol (MCP) server that helps AI agents and AI-native IDEs perform real-world, multi-step tasks across one or more AWS services. The AWS MCP Server consolidates capabilities from the existing AWS API MCP and AWS Knowledge servers into a unified interface, providing access to AWS documentation, generating and executing calls to over 15,000 AWS APIs including those for newly released services, and following pre-built workflows called Agent standard operating procedures (SOPs) that guide AI agents through common tasks on AWS.

With the AWS MCP Server, you can ask AI assistants to perform tasks like hosting static websites on S3, provisioning EC2 instances, troubleshooting Lambda issues, and configuring CloudWatch alarms using Agent SOPs to provide step-by-step guidance. The server handles authentication and authorization through AWS Identity and Access Management (IAM) and provides audit logging through AWS CloudTrail, giving you full control over resources and permissions while enabling AI agents to execute tasks across multiple AWS services helping you complete real-world tasks faster.

The AWS MCP Server is available at no additional cost in the US East (N. Virginia) Region. You pay only for AWS resources you create and applicable data transfer costs. To learn more, see the AWS MCP Server documentation.