AWS Core — Claude Code MCP server: what it does, how to install
AWS Core is an entry point to AWS MCP servers for AI coding tools. Use it when an agent needs AWS context or external tools.
Apache-2.0 ★ 9,939 updated 2026-10-23
Open on GitHubWhat AWS Core does
AWS Core is a collection of specialized MCP servers built for AWS. Through the Model Context Protocol, they give AI applications a standard way to work with added context, external data sources, and tools.
The collection is intended for Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, and Gemini CLI. Treat AWS Core as a gateway to the awslabs server collection rather than a single server for one AWS task.
The Claude Code entry has no install command. Setup therefore happens through the client’s MCP configuration, which is the key detail to account for before connecting it.
What it helps with
- connect an AI coding tool to AWS services
- provide an agent with context from external sources
- choose an AWS MCP server for a project task
- use AWS servers from an MCP-enabled IDE
Example prompts for the agent
- Connect the AWS MCP servers and identify which one fits this project.
- Use AWS context to sketch an architecture for this application.
- Check which external AWS tools are available through MCP.
How to install AWS Core
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 Core
How do I install AWS Core in Claude Code?
In Claude Code, connect AWS Core as an MCP server through the client’s MCP configuration.
What does AWS Core do?
It provides an entry point to a collection of specialized AWS MCP servers. Those servers add context and external tools to AI applications.
Which platforms support AWS Core?
AWS Core is listed for Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, and Gemini CLI.