Log inSubmit server
Awslabs MCP logo

Awslabs MCP

by awslabs

A suite of stdio MCP servers that connects AI applications with AWS documentation, guidance, services, and resources.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Awslabs MCP

Pick your client, then add it in one click or paste the config.

STDIOPython
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "awslabs-mcp": {
      "command": "uvx",
      "args": [
        "awslabs.aws-api-mcp-server@latest"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Install not yet sandbox-tested— we haven't run this command through our automated sandbox yet. Not a red flag; we're working through the catalog.

Overview

The awslabs/mcp MCP server collection connects MCP-compatible AI applications with AWS documentation, contextual guidance, best practices, services, and resources. It is distributed as specialized servers that communicate over standard input and output. Use it when an IDE, chatbot, or other MCP client needs AWS-focused context during cloud development or infrastructure work. The repository also documents client configuration and local or remote deployment considerations.

Use cases

  • Retrieve official AWS documentation in an AI coding workflow
  • Apply AWS guidance to cloud-native development
  • Assist with infrastructure management tasks
  • Connect an MCP client to AWS-focused services and resources

Key features

  • Specialized AWS MCP servers
  • AWS documentation access
  • Contextual guidance and best practices
  • Cloud-native development support
  • Infrastructure management support
  • stdio transport

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked Today

Recent health check succeeded.

29/29 checks healthy over the last 78d

Supply-chain signal

1 high-severity advisory on record for this package. Most advisories affect transitive dependencies and may not be exploitable in this server's actual usage — this is a directional signal, not a security audit.

Critical 0High 1Medium 1Low 2

Scanned 5d ago via OSV.dev · awslabs.aws-api-mcp-server@latest (PyPI)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars9.8kStargazers on the source repository.
Last commitTodayMost recent push to the default branch.
Directory activity3 viewsConfig copies, upvotes, and views on AllMCPs.

How Awslabs MCP works

What awslabs/mcp does

The awslabs/mcp MCP server repository contains a collection of open-source, specialized MCP servers for AWS. Rather than presenting one narrowly scoped service, the repository groups servers intended to add AWS-specific context and capabilities to AI applications. The documented use cases include access to official AWS documentation, contextual guidance, best practices, cloud-native development, infrastructure management, and development workflows.

An MCP host maintains a connection between an AI application and an MCP server. The host may be an AI coding assistant, chatbot, IDE, or another application that supports the Model Context Protocol. This arrangement lets the model request information or capabilities exposed by the connected AWS server while keeping the client-server communication standardized.

The collection fits the Cloud Platforms category because its scope is AWS documentation, services, resources, and cloud development workflows. Choose it when the assistant needs AWS-specific information or tooling rather than a general-purpose local data connector.

How it works

The awslabs/mcp MCP server projects use the Model Context Protocol to expose AWS-oriented capabilities to compatible clients. The repository states that its servers support the stdio transport, which exchanges messages through standard input and standard output. Each server is designed for a one-to-one connection with an MCP client.

The repository describes support for client applications such as Claude Desktop, Cline, Cursor, Windsurf, VS Code, Claude Code, and Kiro. Client configuration is handled in the host application’s MCP settings. The README also distinguishes local servers from remote servers and includes guidance for running servers in containers, although the servers in this repository are designed for stdio communication.

Setup and configuration

Setup depends on which specialized AWS server you select and which MCP client will host it. The repository provides configuration examples or instructions for macOS and Linux, Windows, containers, Cursor, Windsurf, VS Code, Claude Code, Cline with Amazon Bedrock, Kiro, and fx. These examples use the configuration locations supported by each client.

Before connecting a server, select the AWS-focused capability needed by the workflow and add that server to the client’s MCP configuration. The repository’s transport guidance applies to the collection: use stdio rather than Server-Sent Events. The README identifies the servers as open source and provides Apache-2.0 licensing information.

Tools and capabilities

Capabilities described for the awslabs/mcp MCP server collection include:

  • Retrieving or working with official AWS documentation
  • Providing AWS-specific contextual guidance
  • Supplying AWS development best practices
  • Supporting cloud-native development workflows
  • Supporting infrastructure management workflows
  • Connecting AI applications with AWS services and resources

The exact tools available depend on the specialized server selected from the repository. The collection is therefore better treated as a group of AWS MCP servers than as one fixed tool set.

Limitations and notes

The current repository servers support stdio only. Server-Sent Events support was removed from the latest major versions on May 26, 2025.

AWS access, client behavior, and applicable policies remain the user’s responsibility. The repository also notes that the Agent Toolkit for AWS is the successor to the MCP servers, plugins, and skills available from AWS Labs. The MCP repository continues to work and accept contributions, but projects may move to that toolkit over time.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Awslabs MCP

awslabs/mcp is an MCP server collection that connects compatible AI applications with AWS services, resources, and official documentation. Its main capabilities include AWS documentation access, contextual guidance, best-practice assistance, and support for cloud-native development and infrastructure workflows through specialized stdio-based MCP servers.

Install and configure the specific specialized server you need using the repository’s client and platform instructions. The README includes guidance for macOS, Linux, Windows, containers, Cursor, Windsurf, VS Code, Claude Code, Cline, Kiro, and fx.

Yes, awslabs/mcp includes setup guidance for Cursor. Configure the selected AWS MCP server in Cursor’s MCP configuration file and use the repository’s stdio-based transport instructions.

The latest major versions do not support SSE. SSE support was removed on May 26, 2025; the repository is working toward Streamable HTTP, while users who require SSE should use the previous major version of the relevant server.

Related MCP servers

All in Cloud Platforms All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewAwslabs MCP AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/awslabs-mcp?style=directory)](https://allmcps.com/mcp/awslabs-mcp)
HTML Embed
<a href="https://allmcps.com/mcp/awslabs-mcp"><img src="https://allmcps.com/api/badge/awslabs-mcp?style=directory" alt="Awslabs MCP on AllMCPs" /></a>