AWS API — Claude Code MCP server: what it does, how to install
AWS API connects your assistant to AWS resources via AWS CLI commands. Useful when you need to manage cloud infrastructure from the chat.
Apache-2.0 ★ 9,939 updated 2026-10-23
Open on GitHubWhat AWS API does
This bridge lets AI assistants operate across all AWS services. It helps pick valid AWS CLI operations and exposes cloud features released after a model knowledge cutoff date.
Execution options include uvx, standard pip, Docker using an image from public ECR, and streamable HTTP mode. Without configured AWS credentials and Python 3.10 or newer, the server fails to start. You can point to a specific profile with AWS_API_MCP_PROFILE_NAME.
What it helps with
- provision and modify infrastructure via AWS CLI
- call AWS APIs released past the model knowledge cutoff
- isolate cloud interactions inside a Docker container
- stream AWS operations over an HTTP transport
Example prompts for the agent
- List all S3 buckets in region
us-east-1 - Check the status of running EC2 instances via AWS CLI
- Create a standard SQS queue using an AWS command
How to install AWS API
Install
The MCP registry has no launch command for it: see the repository README
Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about AWS API
How to install AWS API in Claude Code?
Add it to your MCP client configuration using the uvx command with argument awslabs.aws-api-mcp-server@latest and the AWS_REGION=us-east-1 environment variable.
What does AWS API do?
It translates AI requests into AWS CLI calls, letting your assistant manage resources across AWS services directly.
What are the runtime requirements?
You need valid AWS credentials and Python 3.10 or higher. You can run it with uvx, via pip, or inside a Docker container.