AWS 官方发布 Agent Toolkit：全面支持 Claude Code、Cursor、Devin 等主流 AI 编程 Agent 构建云上应用

帮助 AI 编程 Agent 在 AWS 上构建、部署和管理应用程序。

Agent Toolkit for AWS 为 AI 编程 Agent 提供了与 AWS 服务协同工作所需的工具、知识和护栏。它支持开发者日常使用的各类编程 Agent，包括 Claude Code、Codex、Cursor、Devin、Kiro 和 fx。

你可以通过 AWS CLI 在终端中直接使用 Agent Toolkit：

aws configure agent-toolkit

有关安装、配置和使用说明，请参阅 AWS CLI 集成指南。

这些插件可在 Anthropic 官方插件市场（claude-plugins-official）中获取，该市场默认已包含在你的 Claude Code 安装中。使用以下命令即可安装工具包中支持的插件：

安装 aws-core（涵盖服务选择、CDK/CloudFormation、无服务器 Serverless、容器、存储、可观测性、账单、SDK 使用以及部署）：

/plugin install aws-core@claude-plugins-official

提示： 如果提示 Plugin not found，请先更新你的本地插件市场索引：

/plugin marketplace update claude-plugins-official

安装 aws-agents（涵盖使用 Amazon Bedrock 和 AgentCore 在 AWS 上构建 AI Agent）：

/plugin install aws-agents@claude-plugins-official

安装 aws-data-analytics（涵盖基于 S3 Tables、AWS Glue 和 Athena 的数据湖、分析及 ETL 工作流）：

/plugin install aws-data-analytics@claude-plugins-official

安装 aws-agents-for-devsecops（用于调查突发事件、审查代码并执行发布就绪的 UAT 验收测试、扫描代码漏洞，以及通过 AWS DevOps Agent 和 AWS Security Agent 运行渗透测试）：

/plugin marketplace add aws/agent-toolkit-for-aws
/plugin install aws-agents-for-devsecops
/reload-plugins

# 或者直接从 Claude 官方市场安装：
/plugin install aws-agents-for-devsecops@claude-plugins-official
/reload-plugins

# 初始化设置：
/aws-agents-for-devsecops:setup

安装 aws-startup-advisor（涵盖面向初创公司的架构、成本、安全和 AWS Activate 指南，以及从 Azure、GCP、Heroku 和包括 OpenAI、Gemini 在内的 AI 技术栈迁移至 AWS），请从本仓库的插件市场安装：

/plugin marketplace add aws/agent-toolkit-for-aws
/plugin install aws-startup-advisor@agent-toolkit-for-aws
/reload-plugins

在终端中运行：

codex plugin marketplace add aws/agent-toolkit-for-aws

然后启动 Codex 并运行 /plugins 来浏览并安装 aws-core 插件。

在 Settings → Plugins → Team Marketplaces → Add Marketplace → Import from Repo 中将本仓库添加为团队市场，指向 aws/agent-toolkit-for-aws。Cursor 在导入时会对 .cursor-plugin/marketplace.json 中列出的插件建立索引。

接着打开 Plugins 面板并安装 aws-core 插件（建议从此处开始），或根据需要安装 aws-agents 和 aws-data-analytics。每个插件都捆绑了 AWS MCP Server 配置和 Agent Skills。

在终端中运行：

devin plugins install aws/agent-toolkit-for-aws#plugins/aws-core

这需要先完成 devin auth login，并将插件添加到你的个人插件中，以便它也能在 Devin 云端会话和 Devin Desktop 中加载。添加 --local 可仅在本机安装。如需安装其他插件，请将 aws-core 替换为对应插件名称，例如 aws-agents 或 aws-data-analytics。

在 Devin Web 应用中，选择 Customize → Plugins → Add plugin → From repository，输入 aws/agent-toolkit-for-aws，并将子目录设置为 plugins/aws-core（或其他插件目录）。在此处添加的个人插件在 Devin CLI 和 Devin Desktop 中同样可用。

Kiro 的配置包含两个独立部分：AWS MCP Server（用于运行时 AWS API 访问与文档检索）和本地技能 Skills（用于特定任务的 Agent 指引）。两者相辅相成但独立工作——技能不强制依赖 MCP 服务器，MCP 服务器也不会提供本地安装的技能。

1. 将 AWS MCP Server 添加至你的 Kiro MCP 配置文件（.kiro/settings/mcp.json）：

{
  "mcpServers": {
    "aws": {
      "command": "uvx",
      "args": [
        "mcp-proxy-for-aws-cli@latest",
        "https://aws-mcp.us-east-1.api.aws/mcp",
        "--metadata",
        "AWS_REGION=us-west-2"
      ]
    }
  }
}

MCP 服务器赋予了 Agent 访问 AWS API、运行沙箱脚本以及实时检索文档的能力。

2. 从本仓库安装技能 Skills：

npx skills add aws/agent-toolkit-for-aws/skills

这会将技能文件安装至 ~/.kiro/skills/（全局）或 .kiro/skills/（项目级）。每个技能都是一个包含 SKILL.md 文件的目录，并可选地包含一个 references/ 子目录，其中存放 Agent 在需要时从本地文件系统读取的补充上下文。Kiro 会自动发现已安装的技能，并在任务匹配时按需激活它们。

先决条件： 需要安装 uv。调用 API 和执行脚本需要配置本地凭据的 AWS 账户，但检索文档或发现技能则不需要。详见用户指南了解完整安装说明。

fx 的配置与 Kiro 一样包含两个独立部分：AWS MCP Server（用于运行时 AWS API 访问与文档检索）和本地技能 Skills（用于特定任务的 Agent 指引）。技能不强制依赖 MCP 服务器，MCP 服务器也不会提供本地安装的技能。

1. 从终端添加 AWS MCP Server。fx 将 MCP 服务器存储在 ~/.fx/mcp.json 中，因此该服务器可在所有项目中通用：

fx mcp add aws uvx mcp-proxy-for-aws-cli@latest https://aws-mcp.us-east-1.api.aws/mcp --metadata AWS_REGION=us-west-2

或者手动将其添加至 ~/.fx/mcp.json。fx 使用 mcp 键而非 mcpServers，使用 type 选择传输方式，并使用单个包含可执行文件及其参数的 command 数组：

{
  "mcp": {
    "aws": {
      "type": "local",
      "command": [
        "uvx",
        "mcp-proxy-for-aws-cli@latest",
        "https://aws-mcp.us-east-1.api.aws/mcp",
        "--metadata",
        "AWS_REGION=us-west-2"
      ]
    }
  }
}

如果在编辑文件时已有会话处于打开状态，请运行 /mcp reload 以应用更改。MCP 服务器赋予了 Agent 访问 AWS API、运行沙箱脚本以及实时检索文档的能力。

2. 从本仓库安装技能 Skills：

npx skills add aws/agent-toolkit-for-aws/skills -a fx

这会将技能文件安装至 .fx/skills/（项目级）；添加 -g 可安装至 ~/.fx/skills/（全局）。fx 还能自动识别为其他 Agent 已安装在 .agents/skills/、.claude/skills/ 和 .codex/skills/ 中的技能，因此针对 Codex 或 Claude Code 配置的项目无需重复复制。每个技能都是一个包含 SKILL.md 文件的目录，并可选地包含一个 references/ 子目录，其中存放 Agent 在需要时从本地文件系统读取的补充上下文。fx 会在启动时读取技能元数据，并在你或 Agent 调用时加载相应指令；在编辑器中输入 $ 或运行 /skills 即可浏览已安装的技能。

先决条件： 需要安装 uv。调用 API 和执行脚本需要配置本地凭据的 AWS 账户，但检索文档或发现技能则不需要。详见用户指南了解完整安装说明。

有关如何为你的 Agent 配置 AWS MCP Server 的说明，请参阅 AWS MCP Server 入门指南。

接着从本仓库安装技能 Skills：

npx skills add aws/agent-toolkit-for-aws/skills

先决条件： 需要安装 uv。调用 API 和执行脚本需要配置本地凭据的 AWS 账户，但检索文档或发现技能则不需要。详见用户指南了解完整安装说明。

插件将 AWS MCP Server 配置和 Agent Skills 打包为单一安装包，方便你的编程 Agent 直接使用。

插件	说明
aws-core	核心 AWS 技能和 MCP Server 配置。涵盖服务选择、CDK/CloudFormation、无服务器 Serverless、容器、存储、可观测性、账单、SDK 使用以及部署。建议从这里开始。
aws-agents	使用 Amazon Bedrock 和 AgentCore 在 AWS 上构建 AI Agent 的相关技能。
aws-data-analytics	适用于 S3 Tables、AWS Glue 和 Athena 的数据湖、分析及 ETL 工作流技能。
aws-agents-for-devsecops	利用 AWS DevOps Agent 和 AWS Security Agent 进行突发事件调查、代码审查、发布就绪 UAT 验收执行、漏洞扫描以及渗透测试。
aws-startup-advisor	将 AWS 初创公司解决方案架构师直接集成到你的编程助手中。根据你所处阶段、云额度与团队规模推荐最具性价比的精简架构，并能自动生成骨架代码、协助从 Azure、Google Cloud 或 Heroku 进行迁移、将模型调用转迁至 Amazon Bedrock、排查生产突发事件、解答 AWS Activate 额度申请资格问题，并为你匹配可用的初创公司优惠权益。

目前支持针对 Claude Code、Codex、Cursor 和 Devin 的插件直接安装。对于其他 Agent，可直接配置 AWS MCP Server 并从本仓库安装技能。

Agent Skills 是经过精心整理的指令集与参考资料包，用于指导 Agent 完成特定的 AWS 任务。技能按需加载——Agent 仅检索并加载与当前任务相关的内容。

npx skills add aws/agent-toolkit-for-aws/skills

浏览 skills/ 目录以查看所有可用技能。

推荐使用的项目级配置文件，指导 Agent 如何最高效地利用 AWS——例如：优先通过 AWS MCP Server 交互、发现可用技能、或在执行操作前检索官方文档。

详情请参见 rules/。

AWS MCP Server 是一项托管服务，通过模型上下文协议（Model Context Protocol）为 Agent 提供访问 AWS 的能力。其提供：

• 全量 AWS API 支持 —— 通过单一已认证端点与 300 多种 AWS 服务进行交互。
• 沙箱化脚本执行 —— Agent 可在隔离环境中运行 Python 脚本，以执行复杂的多步操作。
• 实时文档检索 —— 无需身份凭证即可搜索和获取最新的 AWS 官方文档、API 参考与服务功能细节。
• 企业级管控 —— 集成 Amazon CloudWatch 指标、用于限定 Agent 专用策略的 IAM 上下文键（Context Keys），以及 AWS CloudTrail 审计日志。

有关操作运行、可用工具、身份认证及支持区域的详细信息，请参阅 AWS MCP Server 文档。

Agent Toolkit 与 AWS Labs 中 MCP 服务器、技能及插件的关系

2025 年，AWS 开始作为 AWS Labs 的一部分发布 MCP 服务器、技能和插件。Agent Toolkit for AWS 是这些工具的正统继任者。我们推荐使用 Agent Toolkit for AWS，因为它提供了以下关键特性：

• 能够明确区分 Agent 行为与人类操作的 IAM 条件键（Condition Keys），支持编写仅对 Agent 生效的针对性策略。（例如：即使底层用户的 IAM 角色具备写权限，你也可以编写策略限定通过 MCP 服务器仅能执行只读操作）。
• 针对每次请求记录 CloudWatch 指标与 CloudTrail 审计日志，便于监控和审查编程 Agent 的活动行为。
• 经过全面端到端评估测试的 Agent Skills，确保各类工作流都能可靠、成功地执行完毕。

AWS Labs 的 MCP 服务器、技能和插件将继续运行并接受社区贡献，随着时间推移，AWS Labs 中的优秀成果将逐步迁移到 Agent Toolkit for AWS 中，以确保客户能够获得最广泛的工具和指导生态。

Help AI coding agents build, deploy, and manage applications on AWS.

The 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, Cursor, Devin, Kiro, and fx.

Use the Agent Toolkit directly from your terminal with the AWS CLI:

aws configure agent-toolkit

See the AWS CLI integration guide for setup, configuration, and usage instructions.

The plugins are available on the official Anthropic marketplace (claude-plugins-official) which is added to your Claude Code installation by default. Use the following commands to install supported plugins from the toolkit:

For aws-core that covers service selection, CDK/CloudFormation, serverless, containers, storage, observability, billing, SDK usage, and deployment:

/plugin install aws-core@claude-plugins-official

Tip: If you get Plugin not found, update your local marketplace index first:

/plugin marketplace update claude-plugins-official

For aws-agents that covers building AI agents on AWS with Amazon Bedrock and AgentCore:

/plugin install aws-agents@claude-plugins-official

For aws-data-analytics that covers data lake, analytics, and ETL workflows with S3 Tables, AWS Glue, and Athena:

/plugin install aws-data-analytics@claude-plugins-official

For aws-agents-for-devsecops used to investigate incidents, review code and execute UAT for release readiness, scan code for vulnerabilities, and run penetration tests with AWS DevOps Agent and AWS Security Agent.

/plugin marketplace add aws/agent-toolkit-for-aws
/plugin install aws-agents-for-devsecops
/reload-plugins

# Or from Claude's official marketplace:
/plugin install aws-agents-for-devsecops@claude-plugins-official
/reload-plugins

# Setup:
/aws-agents-for-devsecops:setup

For aws-startup-advisor that covers startup-focused architecture, cost, security, and AWS Activate guidance, plus migrations to AWS from Azure, GCP, Heroku, and AI stacks such as OpenAI and Gemini, install from this repository's marketplace:

/plugin marketplace add aws/agent-toolkit-for-aws
/plugin install aws-startup-advisor@agent-toolkit-for-aws
/reload-plugins

In your terminal:

codex plugin marketplace add aws/agent-toolkit-for-aws

Then launch Codex and run /plugins to browse and install the aws-core plugin.

Add this repository as a team marketplace from Settings → Plugins → Team Marketplaces → Add Marketplace → Import from Repo , pointing it at aws/agent-toolkit-for-aws. Cursor indexes the plugins listed in .cursor-plugin/marketplace.json on import.

Then open the Plugins panel and install the aws-core plugin (start here), or aws-agents and aws-data-analytics as needed. Each plugin bundles the AWS MCP Server configuration and agent skills.

In your terminal:

devin plugins install aws/agent-toolkit-for-aws#plugins/aws-core

This requires devin auth login and adds the plugin to your personal plugins, so it also loads in Devin cloud sessions and Devin Desktop. Add --local to install on this machine only. To install a different plugin, replace aws-core with its name from Plugins, such as aws-agents or aws-data-analytics.

In the Devin web app, choose Customize → Plugins → Add plugin → From repository , enter aws/agent-toolkit-for-aws, and set the subdirectory to plugins/aws-core (or another plugin's directory). Personal plugins added there are also available in the Devin CLI and Devin Desktop.

Kiro setup has two independent parts: the AWS MCP Server (for runtime AWS API access and documentation search) and local skills (for task-specific agent guidance). They complement each other but work independently — skills don't require the MCP server, and the MCP server doesn't serve locally-installed skills.

1. Add the AWS MCP Server to your Kiro MCP configuration (.kiro/settings/mcp.json):

{
  "mcpServers": {
    "aws": {
      "command": "uvx",
      "args": [
        "mcp-proxy-for-aws-cli@latest",
        "https://aws-mcp.us-east-1.api.aws/mcp",
        "--metadata",
        "AWS_REGION=us-west-2"
      ]
    }
  }
}

The MCP server gives your agent access to AWS APIs, sandboxed script execution, and real-time documentation search.

2. Install skills from this repository:

npx skills add aws/agent-toolkit-for-aws/skills

This installs skill files to ~/.kiro/skills/ (global) or .kiro/skills/ (project-level). Each skill is a directory containing a SKILL.md file and optionally a references/ subdirectory with additional context the agent reads from the local filesystem when needed. Kiro discovers installed skills automatically and activates them on demand when a task matches.

Prerequisites: You need uv 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 for detailed setup instructions.

fx setup has the same two independent parts as Kiro: the AWS MCP Server (for runtime AWS API access and documentation search) and local skills (for task-specific agent guidance). Skills don't require the MCP server, and the MCP server doesn't serve locally-installed skills.

1. Add the AWS MCP Server from your terminal. fx stores MCP servers in ~/.fx/mcp.json, so the server is available in every project:

fx mcp add aws uvx mcp-proxy-for-aws-cli@latest https://aws-mcp.us-east-1.api.aws/mcp --metadata AWS_REGION=us-west-2

Or add it to ~/.fx/mcp.json by hand. fx uses the mcp key rather than mcpServers, type to select the transport, and a single command array holding the executable and its arguments:

{
  "mcp": {
    "aws": {
      "type": "local",
      "command": [
        "uvx",
        "mcp-proxy-for-aws-cli@latest",
        "https://aws-mcp.us-east-1.api.aws/mcp",
        "--metadata",
        "AWS_REGION=us-west-2"
      ]
    }
  }
}

If a session is already open when you edit the file, run /mcp reload to pick up the change. The MCP server gives your agent access to AWS APIs, sandboxed script execution, and real-time documentation search.

2. Install skills from this repository:

npx skills add aws/agent-toolkit-for-aws/skills -a fx

This installs skill files to .fx/skills/ (project-level); add -g to install to ~/.fx/skills/ (global). fx also discovers skills already installed for other agents in .agents/skills/, .claude/skills/, and .codex/skills/, so a project set up for Codex or Claude Code needs no second copy. Each skill is a directory containing a SKILL.md file and optionally a references/ subdirectory with additional context the agent reads from the local filesystem when needed. fx reads skill metadata at startup and loads a skill's instructions when you or the agent invokes it; type $ in the composer or run /skills to browse what's installed.

Prerequisites: You need uv 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 for detailed setup instructions.

See the AWS MCP Server getting started guide for instructions on configuring the AWS MCP Server with your agent.

Then install skills from this repository:

npx skills add aws/agent-toolkit-for-aws/skills

Prerequisites: You need uv 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 for detailed setup instructions.

Plugins bundle the AWS MCP Server configuration and agent skills into a single install for your coding agent.

Plugin	Description
aws-core	Core AWS skills and MCP Server configuration. Covers service selection, CDK/CloudFormation, serverless, containers, storage, observability, billing, SDK usage, and deployment. Start here.
aws-agents	Skills for building AI agents on AWS with Amazon Bedrock and AgentCore.
aws-data-analytics	Skills for data lake, analytics, and ETL workflows with S3 Tables, AWS Glue, and Athena.
aws-agents-for-devsecops	Investigate incidents, review code and execute UAT for release readiness, scan code for vulnerabilities, and run penetration tests with AWS DevOps Agent and AWS Security Agent.
aws-startup-advisor	Puts an AWS Startups Solutions Architect in your coding assistant. Recommends the smallest architecture for your stage, credits, and team, then can scaffold it, migrate you from Azure, Google Cloud, or Heroku, move model calls to Amazon Bedrock, investigate production incidents, answer AWS Activate credits eligibility questions, and find startup offers you can use.

Plugins are currently available for Claude Code, Codex, Cursor, and Devin. For other agents, configure the AWS MCP Server directly and install skills from this repository.

Agent 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.

npx skills add aws/agent-toolkit-for-aws/skills

Browse the skills/ directory to see all available skills.

Recommended 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.

See rules/ for details.

The AWS MCP Server is a managed server that gives agents access to AWS through the Model Context Protocol. It provides:

• Full AWS API coverage — Interact with any of the 300+ AWS services through a single authenticated endpoint.
• Sandboxed script execution — Agents can run Python scripts in an isolated environment for complex multi-step operations.
• Real-time documentation access — Search and retrieve current AWS documentation, API references, and service capabilities without authentication.
• Enterprise controls — Amazon CloudWatch metrics, IAM context keys for agent-specific policies, and AWS CloudTrail audit logging.

For details on operation, available tools, authentication, and supported Regions, see the AWS MCP Server documentation.

How the Agent Toolkit relates to the MCP servers, skills, and plugins in AWS Labs

In 2025, AWS began releasing MCP servers, skills, and plugins as part of AWS Labs. 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:

• 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).
• CloudWatch metrics and CloudTrail audit logging for every request, so you can monitor and audit coding agent activity.
• Agent skills that have undergone thorough end-to-end evaluations, so you can be confident that workflows will complete successfully.

AWS Labs 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.

This project is licensed under the Apache-2.0 License. See LICENSE for details.