mcp

MCP.Pizza Chef: awslabs

Rather than one big install, this is a shelf of small servers from Amazon and you pick only the ones you want: current documentation, cost estimates before you build, billing figures afterwards, architecture diagrams, container and serverless helpers, and database access. Most of them need cloud credentials set up on your computer first, so the documentation one is the gentlest place to start. They plug into Cursor, VS Code, Cline, Windsurf, Claude Desktop and Kiro, each added with its own short settings block.

Coding
Data

Use This MCP server To

Estimate what a setup will cost before building it Get answers from current Amazon documentation Draw an architecture diagram from a description Check where last month's cloud bill went Look up the recommended way to configure a service

README

AWS MCP Servers

A suite of specialized MCP servers that help you get the most out of AWS, wherever you use MCP.

GitHub License Codecov OSSF-Scorecard Score

Table of Contents

What is the Model Context Protocol (MCP) and how does it work with AWS MCP Servers?

The Model Context Protocol (MCP) is an open protocol that enables seamless integration between LLM applications and external data sources and tools. Whether you're building an AI-powered IDE, enhancing a chat interface, or creating custom AI workflows, MCP provides a standardized way to connect LLMs with the context they need.

— Model Context Protocol README

mcp FAQ

Do I need an Amazon account?
For most of them, yes — you set up cloud credentials on your computer first. The documentation server is the easiest starting point.
Which apps does it work in?
Cursor, VS Code, Cline, Windsurf, Claude Desktop, Kiro and other MCP clients.
Can I use this to estimate what something will cost?
Yes — the pricing server gives estimates before you build, and a billing server shows what you already spent.
Do I have to install all of them?
No. Each server is separate, so add only the ones you need.
How hard is setup?
Developer level: install the uv tool, then paste a settings block for each server you want.
Is it still maintained?
Yes. Amazon now also offers a newer Agent Toolkit aimed at production use, and this collection keeps working and accepting contributions.