What is the Agent Toolkit for AWS?

AWS MCP Server — A managed server that gives agents access to AWS through the Model Context Protocol (MCP). Agents can search AWS documentation and retrieve service information without authentication. To execute AWS API calls, run Python scripts in a sandboxed environment, or follow curated skills, agents authenticate through your existing IAM credentials. All of these capabilities are available through a single endpoint with CloudWatch metrics and IAM-based access controls.

Agent skills — Curated packages of instructions, code scripts, and reference materials that help agents complete specific AWS tasks. Skills are loaded on demand — agents discover and retrieve only the skills relevant to the current task, so they do not consume unnecessary context. Skills cover service selection, step-by-step procedures, troubleshooting, and SDK best practices.

Plugins — Single-install packages for Claude Code and Codex that bundle the AWS MCP Server configuration and a curated set of agent skills. After you install a plugin, your agent is ready to work with AWS.

Rules files — Project-level configuration files that set guardrails and preferences for how agents work in your project. Rules files tell agents how to use AWS most effectively — for example, by using the AWS MCP Server, discovering available skills, or searching documentation before acting.

Build and deploy applications on AWS — Your agent creates AWS infrastructure, writes application code, and deploys to production. Skills from the toolkit guide your agent through choosing the right services, configuring them correctly, and following deployment best practices.

Stay up to date on the latest AWS services — The AI models that power coding agents are trained on data that can be months or years old. Newer AWS services and recently launched features are often missing from an agent's knowledge. The toolkit gives your agent real-time access to current AWS documentation, API references, and service capabilities.

Follow tested procedures for complex workflows — Instead of improvising from general knowledge, your agent follows tested procedures provided by the toolkit for workflows like configuring least-privilege IAM policies, setting up data pipelines, or deploying production-ready serverless applications.

Troubleshoot operational issues — Point your agent at a failing deployment, a spike in error rates, or an unexpected cost increase. The toolkit provides skills that help your agent work with CloudWatch logs and metrics, CloudFormation stack status, and troubleshooting procedures.

Operate with security and visibility — The AWS MCP Server provides CloudWatch metrics for monitoring agent activity, IAM-based access controls, and the ability to set enterprise guardrails — like restricting agents to read-only operations or blocking specific actions through MCP.

Work with any MCP-compatible agent — The Agent Toolkit for AWS works with Claude Code, Cursor, Codex, Kiro, Windsurf, Cline, and any other agent that supports the Model Context Protocol.

Skills provide structured guidance — The agent uses skills that are installed locally via a plugin, or discovers them at runtime through the AWS MCP Server. Skills contain step-by-step instructions, decision guides, and reference materials that guide the agent through complex procedures while following AWS best practices.

Knowledge tools provide current information — When the agent needs up-to-date information, it can search AWS documentation, retrieve API references, check regional availability, and access the latest AWS service information.

API tools execute authenticated actions — The AWS MCP Server translates requests into properly formatted AWS API calls, handles authentication using your IAM credentials, and executes the commands with detailed feedback about results and any errors. For complex multi-step operations, agents can write and execute Python scripts in an isolated sandbox using the run_script tool.