kirodotdev/powers

Powers add specialized context and tools to the Kiro agents on-demand. No more MCP context overload.

What it solves

Kiro powers provide a collection of specialized tools and workflows that enhance the capabilities of AI agents. They bridge the gap between general-purpose LLMs and specific technical tasks, such as cloud infrastructure management, code migration, and API integration, by providing agents with the necessary context, documentation, and execution tools.

How it works

Each "power" is a set of capabilities that can be integrated into an AI agent. Many of these powers utilize Model Context Protocol (MCP) servers to give agents real-time access to external APIs, documentation, and system executions. This allows agents to perform multi-step tasks—like migrating code between Arm SoCs or managing AWS resources—by combining knowledge bases with active tooling.

Who it’s for

This project is primarily for developers and DevOps engineers who use AI agents to automate complex technical workflows, particularly those working within the AWS ecosystem or using modern cloud-native tools like Databricks, Neon, or Terraform.

Highlights

  • AWS Ecosystem Integration: Extensive powers for Bedrock AgentCore, CDK, CloudFormation, Lambda, and AWS observability tools.
  • MCP-Driven: Leverages Model Context Protocol servers to provide agents with live tools and syntactically correct API executions.
  • Migration Tooling: Specialized powers for migrating code between different Arm SoCs and moving workloads from GCP to AWS.
  • Broad Integration Range: Includes powers for third-party services like Zapier, Datadog, Dynatrace, Postman, and Checkout.com.

Related

  • Project
    aws/agent-toolkit-for-aws

    A collection of tools, plugins, and skills that enable AI coding agents to securely build, deploy, and manage AWS infrastructure using the Model Context Protocol.

  • Project
    awslabs/agent-plugins

    A collection of plugins for AI coding agents that provide specialized skills, MCP servers, and workflows to help developers architect, deploy, and operate on AWS.

  • Project
    cloudflare/skills

    A plug‑in library that adds Cloudflare‑specific “Agent Skills” to AI coding assistants (Claude Code, Codex, Cursor, VS Code, etc.). Each skill teaches the agent how to work with a Cloudflare product—Workers, Wrangler, Durable Objects, Turnstile, Cloudflare One, and more—by providing up‑to‑date docs, CLI commands, and API calls via Cloudflare’s remote MCP server. Install via the native plugin marketplace of the target agent or manually copy the skill folders.

  • Project
    microsoft/azure-devops-mcp

    An MCP server that enables AI agents to interact with Azure DevOps, allowing them to manage work items, repositories, wikis, and pipelines through natural language.

  • Project
    astronomer/agents

    AI agent tooling for data engineering that extends AI coding agents with specialized skills and an MCP server for managing Apache Airflow and querying data warehouses.