Observed Signal · Apr 5, 2026 · Technical Release · Source: DEV Community · Impact: 4/5 · Sentiment: Positive
AWS Agent Plugins for Claude Code via kiro-gateway
AWS released "Agent Plugins for AWS," a package of structured skill packs (skills, MCP servers, hooks, references) that integrate with Claude Code to automate serverless, deployment, SageMaker workflows and more. The author tested the plugins by routing Claude Code through a local kiro-gateway tied to an existing Kiro Pro subscription (no extra API subscription required). The post documents installation steps, available plugins (seven marketplace plugins including deploy-on-aws, aws-serverless, and sagemaker-ai), a live cost-estimation example (using the AWS Price List API) showing roughly $0.40/month for a 10,000-requests/day serverless TODO API, end-to-end deployment flows (SAM/CDK), and two troubleshooting fixes: a 64-character tool-name limit in Kiro requiring a name-shortening patch, and an Apple Silicon build fix for aws-iac-mcp (rustup target add x86_64-apple-darwin).
Major cloud provider (AWS) released technical agent plugin tooling that integrates LLM agents (Claude Code) with live pricing, deployment and SageMaker workflows. This enables agent-driven developer workflows, live cost estimation and end-to-end IaC deployments — capabilities that can accelerate adoption of agents in engineering and martech stacks.
Track Anthropic Signals & Market Shifts in Real-Time
Polaris7 autonomous intelligence agents track regulatory filings, primary sources, executive changes, and deal flow 24/7. Create your free Explorer workspace to monitor these entities.
Key Takeaways & Evidence Grounding
- AWS published Agent Plugins for AWS which package skills, MCP servers, hooks, and references for Claude Code.
- Claude Code can be pointed to a local kiro-gateway via the ANTHROPIC_BASE_URL environment variable; routing through kiro-gateway lets a Kiro Pro subscription be used without an extra API key.
- Seven plugins are available in the marketplace: deploy-on-aws, aws-serverless, aws-amplify, databases-on-aws, amazon-location-service, migration-to-aws, and sagemaker-ai.
- The deploy-on-aws plugin runs a five-step workflow (Analyze, Recommend, Estimate, Generate, Deploy) and calls the AWS Price List API for live cost estimates; an example 10,000 requests/day serverless TODO API estimated at ~$0.40/month.
- Two reported issues and fixes: (1) long MCP-generated tool names exceeded Kiro's 64-character limit — the author patched kiro-gateway to shorten names; (2) aws-iac-mcp failed to build on Apple Silicon — fixed by running `rustup target add x86_64-apple-darwin`.
Connected Companies & Entities
2 Entities mappedOntology Mapping & Concepts
Related Market Signals & Shifts
Recent verified developments and strategic activity across this market segment.
AWS Agent Toolkit Enables Secure AI Agent Access
A developer describes switching from community MCP servers to the Agent Toolkit for AWS, an AWS-managed suite that gives AI coding agents controlled, auditable access to AWS. The toolkit bundles a managed AWS MCP Server, curated Skills, IDE Plugins, and project-level Rules files. Key security features include IAM condition keys and request tagging (aws:CalledViaAWSMCP) so administrator policies can restrict agent actions. The toolkit provides a sandboxed Python runtime with boto3 for remote code execution, and all MCP-initiated API calls are visible via CloudTrail and CloudWatch. It supports multi-profile (multiple AWS accounts) and built-in documentation search. The Agent Toolkit is free to use; standard AWS resource charges apply. The article includes configuration examples (Kiro) and notes default MCP quotas (3 requests/second/account). Published 2026-06-12.
AWS Kiro: Amazon's AI Coding Agent for Dev & DevOps
AWS Kiro is an AI-powered coding agent from Amazon that integrates with Amazon Bedrock models to assist developers and DevOps engineers. It ships as two main interfaces — Kiro IDE (a VS Code / Code OSS fork with built-in AI capabilities) and Kiro CLI (a terminal-based agent for automating DevOps and infrastructure tasks). Kiro offers Spec-Driven Development (Spec Mode) to generate user stories, DB schemas and data flows from natural language, an agent workflow that reads repos and orchestrates code and tests, and terminal-driven DevOps operations (e.g., deploy to S3, analyze CloudWatch logs). The tool supports extensibility through MCP (Model Context Protocol) to connect private knowledge bases and external APIs, positioning Kiro as an agentic assistant for AWS development workflows.
AWS launches Kiro Crew orchestration platform
AWS introduced Kiro Crew, an open-source orchestration platform designed to turn AI coding agents into persistent, autonomous engineering teammates. Kiro Crew coordinates multiple agents, maintains project context across sessions with persistent memory, schedules recurring work, and integrates with developer tools while offering security features such as sandboxing and signed audit logs. The project was previously an internal Amazon tool called MeshClaw, adopted by over 39,000 Amazon builders in under six months. AWS published reference applications (DevFleets, Issue Radar, Task Runner), will allow self-hosted deployments, and plans public governance via a steering committee. The platform uses open standards (Agent Client Protocol, Model Context Protocol) but initially ships with a proprietary Kiro CLI.
Track Real-Time Market Signals & Shifts
Set up custom watchlists to receive automated, evidence-grounded executive digests whenever material signals or shifts occur across your tracked landscape.