[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-11078":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":10,"rankLanguage":10,"license":22,"archived":23,"fork":23,"defaultBranch":24,"hasWiki":23,"hasPages":23,"topics":25,"createdAt":10,"pushedAt":10,"updatedAt":26,"readmeContent":27,"aiSummary":28,"trendingCount":16,"starSnapshotCount":16,"syncStatus":29,"lastSyncTime":30,"discoverSource":31},11078,"agent-toolkit-for-aws","aws\u002Fagent-toolkit-for-aws","aws","Official, AWS-supported MCP servers, skills, and plugins to help AI agents build on AWS","",null,"Python",840,77,8,5,0,45,72,269,135,9.68,"Apache License 2.0",false,"main",[],"2026-06-12 02:02:29","# Agent Toolkit for AWS\n\n[![License](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-Apache%202.0-blue.svg)](LICENSE)\n[![Build](https:\u002F\u002Fgithub.com\u002Faws\u002Fagent-toolkit-for-aws\u002Factions\u002Fworkflows\u002Fbuild.yml\u002Fbadge.svg)](https:\u002F\u002Fgithub.com\u002Faws\u002Fagent-toolkit-for-aws\u002Factions\u002Fworkflows\u002Fbuild.yml)\n[![Status](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fstatus-GA-green.svg)](https:\u002F\u002Fgithub.com\u002Faws\u002Fagent-toolkit-for-aws)\n\nHelp AI coding agents build, deploy, and manage applications on AWS.\n\nThe Agent Toolkit for AWS gives AI coding agents the tools, knowledge, and guardrails they need to work with AWS services. It works with the coding agents developers already use — including Claude Code, Codex, and Kiro.\n\n## Quick start\n\n### Claude Code\n\nThe plugins are available on the official Anthropic marketplace (`claude-plugins-official`) which is added to your Claude Code installation by default.\nUse the following commands to install supported plugins from the toolkit:\n\nFor `aws-core` that covers service selection, CDK\u002FCloudFormation, serverless, containers, storage, observability, billing, SDK usage, and deployment:\n\n```\n\u002Fplugin install aws-core@claude-plugins-official\n```\n\nFor `aws-agents` that covers building AI agents on AWS with Amazon Bedrock and AgentCore:\n\n```\n\u002Fplugin install aws-agents@claude-plugins-official\n```\n\nFor `aws-data-analytics` that covers data lake, analytics, and ETL workflows with S3 Tables, AWS Glue, and Athena:\n\n```\n\u002Fplugin install aws-data-analytics@claude-plugins-official\n```\n\n### Codex\n\nIn your terminal:\n\n```\ncodex plugin marketplace add aws\u002Fagent-toolkit-for-aws\n```\n\nThen launch Codex and run `\u002Fplugins` to browse and install the **aws-core** plugin.\n\n### Kiro\n\nAdd the AWS MCP Server to your Kiro MCP configuration (`.kiro\u002Fsettings\u002Fmcp.json`):\n\n```json\n{\n  \"mcpServers\": {\n    \"aws\": {\n      \"command\": \"uvx\",\n      \"args\": [\n        \"mcp-proxy-for-aws@latest\",\n        \"https:\u002F\u002Faws-mcp.us-east-1.api.aws\u002Fmcp\",\n        \"--metadata\", \"AWS_REGION=us-west-2\"\n      ]\n    }\n  }\n}\n```\n\nThen install skills from this repository:\n\n```\nnpx skills add aws\u002Fagent-toolkit-for-aws\u002Fskills\n```\n\n> **Prerequisites:** You need [uv](https:\u002F\u002Fdocs.astral.sh\u002Fuv\u002F) installed. An AWS account with credentials configured locally is required for API calls and script execution, but not for documentation search or skill discovery. See the [user guide](https:\u002F\u002Fdocs.aws.amazon.com\u002Fagent-toolkit\u002Flatest\u002Fuserguide\u002F) for detailed setup instructions.\n\n### Other agents\n\nSee the [AWS MCP Server getting started guide](https:\u002F\u002Fdocs.aws.amazon.com\u002Fagent-toolkit\u002Flatest\u002Fuserguide\u002Fgetting-started-aws-mcp-server.html) for instructions on configuring the AWS MCP Server with your agent.\n\nThen install skills from this repository:\n\n```\nnpx skills add aws\u002Fagent-toolkit-for-aws\u002Fskills\n```\n\n> **Prerequisites:** You need [uv](https:\u002F\u002Fdocs.astral.sh\u002Fuv\u002F) installed. An AWS account with credentials configured locally is required for API calls and script execution, but not for documentation search or skill discovery. See the [user guide](https:\u002F\u002Fdocs.aws.amazon.com\u002Fagent-toolkit\u002Flatest\u002Fuserguide\u002F) for detailed setup instructions.\n\n## What's included\n\n### Plugins\n\nPlugins bundle the AWS MCP Server configuration and agent skills into a single install for your coding agent.\n\n| Plugin | Description |\n|--------|-------------|\n| [aws-core](plugins\u002Faws-core\u002F) | Core AWS skills and MCP Server configuration. Covers service selection, CDK\u002FCloudFormation, serverless, containers, storage, observability, billing, SDK usage, and deployment. **Start here.** |\n| [aws-agents](plugins\u002Faws-agents\u002F) | Skills for building AI agents on AWS with Amazon Bedrock and AgentCore. |\n| [aws-data-analytics](plugins\u002Faws-data-analytics\u002F) | Skills for data lake, analytics, and ETL workflows with S3 Tables, AWS Glue, and Athena. |\n\nPlugins are currently available for Claude Code and Codex. For other agents, configure the AWS MCP Server directly and install skills from this repository.\n\n### Skills\n\nAgent skills are curated packages of instructions and reference materials that help agents complete specific AWS tasks. Skills are loaded on demand — agents discover and retrieve only what's relevant to the current task.\n\n```\nnpx skills add aws\u002Fagent-toolkit-for-aws\u002Fskills\n```\n\nBrowse the [`skills\u002F`](skills\u002F) directory to see all available skills.\n\n### Rules files\n\nRecommended project-level configuration files that tell agents how to use AWS most effectively — for example, by using the AWS MCP Server, discovering available skills, or searching documentation before acting.\n\nSee [`rules\u002F`](rules\u002F) for details.\n\n### AWS MCP Server\n\nThe [AWS MCP Server](https:\u002F\u002Fdocs.aws.amazon.com\u002Fagent-toolkit\u002Flatest\u002Fuserguide\u002Funderstanding-mcp-server-tools.html) is a managed server that gives agents access to AWS through the Model Context Protocol. It provides:\n\n- **Full AWS API coverage** — Interact with any of the 300+ AWS services through a single authenticated endpoint.\n- **Sandboxed script execution** — Agents can run Python scripts in an isolated environment for complex multi-step operations.\n- **Real-time documentation access** — Search and retrieve current AWS documentation, API references, and service capabilities without authentication.\n- **Enterprise controls** — Amazon CloudWatch metrics, IAM context keys for agent-specific policies, and AWS CloudTrail audit logging.\n\nFor details on operation, available tools, authentication, and supported Regions, see the [AWS MCP Server documentation](https:\u002F\u002Fdocs.aws.amazon.com\u002Fagent-toolkit\u002Flatest\u002Fuserguide\u002Funderstanding-mcp-server-tools.html).\n\n## Documentation\n\n- [User guide](https:\u002F\u002Fdocs.aws.amazon.com\u002Fagent-toolkit\u002Flatest\u002Fuserguide\u002F) — Setup, configuration, and reference documentation.\n- [AWS MCP Server tools](https:\u002F\u002Fdocs.aws.amazon.com\u002Fagent-toolkit\u002Flatest\u002Fuserguide\u002Funderstanding-mcp-server-tools.html) — Reference for all available MCP tools.\n\n## How the Agent Toolkit relates to the MCP servers, skills, and plugins in AWS Labs\nIn 2025, AWS began releasing MCP servers, skills, and plugins as part of [AWS Labs](https:\u002F\u002Fgithub.com\u002Fawslabs). The Agent Toolkit for AWS is the successor to those tools. We recommend using the Agent Toolkit for AWS, because it offers key features including:\n\n- IAM condition keys that distinguish between agent actions and human actions, so you can write policies that apply only to agents. For example, you can write policies that only allow read-only actions through the MCP server, even if the user’s underlying IAM role can take write actions).\n- CloudWatch metrics and CloudTrail audit logging for every request, so you can monitor and audit coding agent activity.\n- Agent skills that have undergone thorough end-to-end evaluations, so you can be confident that workflows will complete successfully.\n\n[AWS Labs](https:\u002F\u002Fgithub.com\u002Fawslabs) MCP servers, skills, and plugins will continue to work and accept contributions, and over time the best of AWS Labs will be transitioned to the Agent Toolkit for AWS to ensure that customers can access the broadest array of tooling and guidance for their agents.\n\n## License\n\nThis project is licensed under the Apache-2.0 License. See [LICENSE](LICENSE) for details.\n","Agent Toolkit for AWS 是一个由 AWS 官方支持的工具包，旨在帮助 AI 编码代理在 AWS 上构建、部署和管理应用程序。该项目提供了丰富的插件与技能，包括服务选择、CDK\u002FCloudFormation、无服务器架构、容器、存储、可观测性、计费、SDK 使用以及部署等核心功能，适用于 Claude Code、Codex 和 Kiro 等多种开发环境。其设计目的是为开发者提供一套完整的工具集，使他们能够更高效地利用 AWS 服务进行开发工作。特别适合那些希望提升基于 AWS 的 AI 应用程序开发效率或自动化程度的场景使用。项目采用 Python 编写，并遵循 Apache License 2.0 开源许可协议。",2,"2026-06-11 03:31:10","CREATED_QUERY"]