Integrating AWS API MCP Server with Amazon Quick using Amazon Bedrock AgentCore Runtime

2026-05-21 · Source: Artificial Intelligence · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Cloud Computing & IT Infrastructure, Cybersecurity & Data Privacy · Depth: Intermediate, long

Summary

This post details integrating the AWS API MCP Server with Amazon Quick via Amazon Bedrock AgentCore Runtime to establish a conversational AI assistant for managing AWS infrastructure. The solution enables SREs and DevOps Engineers to execute AWS CLI commands using natural language queries, eliminating the need for manual context-switching between the AWS Management Console, CLI documentation, and service dashboards. It outlines a manual deployment process involving setting up an Amazon Cognito user pool for JWT authentication, creating specific IAM trust and execution roles, configuring an Amazon Bedrock AgentCore Runtime agent with ECR container image access, and finally, creating a custom chat agent in Amazon Quick. The system ensures secure execution within existing IAM permissions and provides Amazon CloudWatch audit trails. A single Enterprise user performing 500 queries per month incurs an estimated cost of \$292/month.

Key takeaway

For SREs and DevOps Engineers aiming to streamline AWS operational workflows, implementing this conversational AI assistant changes how you interact with your infrastructure. You can manage AWS services using natural language queries, eliminating manual API syntax translation and the need to rebuild integrations for each use case. This approach enhances efficiency, ensures secure command execution via IAM, and provides full CloudWatch audit trails. Consider deploying this solution to reduce context-switching and automate common operational tasks.

Key insights

Conversational AI streamlines AWS operations by translating natural language into secure CLI commands via Bedrock AgentCore and MCP.

Principles

• Standardize AI agent interaction with AWS services.
• Enforce least-privilege IAM for API execution.
• AgentCore Runtime handles JWT token validation as a security boundary.

Method

Configure Amazon Cognito for JWT authentication, create IAM roles for AgentCore Runtime, deploy AWS API MCP Server as an AgentCore Runtime agent, then integrate and build a custom chat agent in Amazon Quick.

In practice

• Query running EC2 instances in natural language.
• Automate operational queries for security or cost optimization.
• Integrate with incident management workflows using Quick Flows.

Topics

• AWS API MCP Server
• Amazon Quick
• Amazon Bedrock AgentCore Runtime
• Conversational AI
• AWS CLI Automation
• IAM Security

Code references

• awslabs/mcp

Best for: MLOps Engineer, DevOps Engineer, AI Engineer

Related on AIssential

• Integrating Amazon Bedrock AgentCore with Slack — Integrate Amazon Bedrock AgentCore with Slack for in-workspace AI agents, managing security, context, and timeouts.
• Extending MCP support for Amazon Bedrock AgentCore Gateway — AgentCore Gateway centralizes MCP server governance, enabling scalable, secure, and stateful enterprise agent workflows.
• OpenAI models now available on Amazon Web Services — OpenAI's GPT-5.5, GPT-5.4, and Codex are now available on AWS Bedrock, integrating with existing AWS infrastructure and security.
• An Interview with OpenAI CEO Sam Altman and AWS CEO Matt Garman About Bedrock Managed Agents — AI agent development requires deep integration of models with cloud-native runtime environments for enterprise adoption.
• aws / agent-toolkit-for-aws — AI coding agents can now securely and effectively interact with AWS services through a specialized toolkit providing tools, knowledge, and guardrails.
• AWS Bedrock Agents: The Beginner’s Guide — AWS Bedrock Agents provide a managed platform for building and deploying AI agents with integrated orchestration and security.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Artificial Intelligence.