awslabs/mcp

★ 9,039PythonAudience · developerComplexity · 3/5Setup · moderate

Mindmap

mindmap
  root((AWS MCP Servers))
    What it does
      Connects AI to AWS
      Chat-driven deployment
      Documentation lookup
    AWS Services
      CDK CloudFormation
      Serverless containers
      Databases analytics
    Supported AI Tools
      Claude Cursor
      VS Code Windsurf
    Setup
      pip install per server
      JSON config snippet
    Audience
      AWS developers
      DevOps engineers

mindmap root((AWS MCP Servers)) What it does Connects AI to AWS Chat-driven deployment Documentation lookup AWS Services CDK CloudFormation Serverless containers Databases analytics Supported AI Tools Claude Cursor VS Code Windsurf Setup pip install per server JSON config snippet Audience AWS developers DevOps engineers

Click or tap to explore — scroll the page freely

Things people build with this

USE CASE 1

Ask Claude or Cursor to look up official AWS documentation and generate CloudFormation or CDK infrastructure code without leaving your editor

USE CASE 2

Query an RDS or DynamoDB database through an AI assistant chat window without switching tools or writing connection code manually

USE CASE 3

Deploy serverless or containerized workloads on AWS by chatting with an AI tool that has the appropriate MCP server configured

USE CASE 4

Add AWS documentation lookup to VS Code AI so you get accurate answers about AWS APIs without copying and pasting from a browser

Tech stack

PythonAWS

Getting it running

Difficulty · moderate Time to first run · 30min

Requires an AWS account with appropriate IAM permissions and an MCP-compatible AI tool such as Claude, Cursor, or VS Code Copilot.

In plain English

This repository is a collection of open-source MCP servers built by AWS Labs. MCP stands for Model Context Protocol, an open standard created by Anthropic that lets AI coding assistants and chatbots connect to external tools and data sources in a consistent way. When you configure one of these servers alongside a tool like Claude, Cursor, Windsurf, or VS Code's AI features, the AI can query AWS documentation, deploy infrastructure, run database queries, and more, all from within a chat interface. The collection covers a wide range of AWS services. There are servers for looking up official AWS documentation, generating and applying infrastructure-as-code with CDK or CloudFormation, working with serverless and containerized workloads, querying SQL and NoSQL databases, running analytics, managing caching layers, and handling healthcare and life-sciences workflows. Each server is an independent Python package you install and configure separately. Installing a server typically means running pip install and adding a short JSON configuration block to your AI tool's settings file. The README includes ready-to-paste configuration snippets for Claude Code, Cursor, Windsurf, VS Code, Cline, and Kiro. The servers communicate over standard input and output by default, so they do not open any network port unless you configure a remote transport. AWS Labs notes that this collection is evolving into something called the Agent Toolkit for AWS, which includes finer-grained IAM permission controls, CloudWatch logging, and built-in accuracy evaluations intended for production deployments. The MCP servers in this repository continue to work and accept contributions, over time the most useful ones are expected to move into the Agent Toolkit. The full README is longer than what was shown.

Copy-paste prompts

Prompt 1

I've installed the AWS MCP documentation server. Help me add the correct configuration block to my Claude Code settings so I can ask AWS S3 permission questions from my coding session.

Prompt 2

Using the AWS CDK MCP server, generate a TypeScript CDK stack that creates an S3 bucket with versioning and a Lambda function triggered by new uploads.

Prompt 3

Help me set up the AWS RDS MCP server so I can query my PostgreSQL database on AWS from a Cursor AI chat window without writing any connection code.

Prompt 4

Walk me through adding an AWS MCP server config snippet to my VS Code settings so the AI assistant can look up and apply CloudFormation templates on my behalf.

Open on GitHub → Explain another repo

← awslabs on gitmyhub — every repo by this author, as a profile.

Verify against the repo before relying on details.