As AWS infrastructure scales, operational workflows naturally grow more complex. SREs and DevOps Engineers spend significant time context-switching between the AWS Management Console, CLI documentation, and multiple service dashboards. They manually translate business questions into the correct API syntax, chain calls across services, and rebuild the same integration patterns for each new use case.
This friction compounds over time. Incident investigations require cross-referencing Amazon CloudWatch Logs, Amazon EC2 instance states, and IAM policies across separate interfaces. Capacity planning means manually querying multiple services and assembling results, while security audits demand consistent, repeatable API call sequences that are time-consuming to script from scratch.
This post demonstrates how to use Amazon Bedrock AgentCore Runtime with Model Context Protocol (MCP) support to connect Amazon Quick with AWS services through the AWS API MCP Server. This setup creates a conversational AI assistant that translates natural language into AWS Command Line Interface (AWS CLI) commands, eliminating the need to switch tools during critical moments.
With MCP support, natural language queries translate directly to AWS API calls. Users can ask, "Show me all running EC2 instances in us-east-1," and receive accurate results without memorizing syntax. Requests run securely within existing IAM permissions, featuring full Amazon CloudWatch audit trails. This allows teams to standardize how AI agents interact with AWS services through a single, reusable integration.
The operational workflow functions as follows: 1. A natural language question is posed; 2. The Amazon Quick agent interprets the intent; 3. Amazon Cognito authenticates the request using OAuth 2.0 to obtain a JWT token; 4. AgentCore Runtime validates the token and routes the request; 5. The AWS API MCP Server in a containerized environment translates the query into the appropriate AWS CLI command; 6. AWS services execute the command using configured IAM roles.
