Skip to main content
mcpSource-backedReview first Safety Privacy
AWS Labs logo

AWS Documentation MCP Server

Official AWS Labs MCP server that lets AI assistants read, search, and get recommendations across AWS documentation, returning pages as clean markdown with no AWS account or credentials required.

by AWS Labs·added 2026-06-20·
HarnessClaude CodeCodexCursorClaude Desktop
Review first review before installing

Open the source and read safety notes before installing.

Citation facts

Source-backed facts for citing this resource, derived directly from the registry — also available as plain text for AI assistants.

Source URLs
https://github.com/awslabs/mcp, https://awslabs.github.io/mcp/
Brand
AWS Labs
Brand domain
aws.amazon.com
Brand asset source
brandfetch
Safety notes
The server is read-only: it fetches and searches public AWS documentation and does not call AWS service APIs or modify any AWS resources., It requires no AWS account or credentials; do not add AWS access keys for this server., `AWS_DOCUMENTATION_PARTITION` selects the docs partition (`aws` global, or `aws-cn` for China); the available tools differ between partitions.
Privacy notes
Documentation URLs and search terms you ask about are sent to the official AWS documentation search/read endpoints to retrieve content., The server fetches public documentation pages over HTTPS and returns them as markdown; no private account data is read.
Author
AWS Labs
Submitted by
jaso0n0818
Claim status
unclaimed
Last verified
2026-06-20

Safety notes

  • The server is read-only: it fetches and searches public AWS documentation and does not call AWS service APIs or modify any AWS resources.
  • It requires no AWS account or credentials; do not add AWS access keys for this server.
  • `AWS_DOCUMENTATION_PARTITION` selects the docs partition (`aws` global, or `aws-cn` for China); the available tools differ between partitions.

Privacy notes

  • Documentation URLs and search terms you ask about are sent to the official AWS documentation search/read endpoints to retrieve content.
  • The server fetches public documentation pages over HTTPS and returns them as markdown; no private account data is read.

Prerequisites

  • Python 3.10 or newer installed.
  • `uv` / `uvx` installed (Astral) to run the published Python package.
  • An MCP client that supports stdio servers (Claude Code, Claude Desktop, Cursor, Kiro, or VS Code).
  • Outbound HTTPS access so the server can fetch and search AWS documentation.

Schema details

Install type
cli
Troubleshooting
No
Source repository stats
Scope
Source repo
Collection metadata
Estimated setup
5 minutes
Difficulty
beginner
Tool listing metadata
Pricing
open-source
Disclosure
editorial
Application category
DeveloperApplication
Operating system
Cross-platform
Full copyable content
{
  "awslabs.aws-documentation-mcp-server": {
    "command": "uvx",
    "args": ["awslabs.aws-documentation-mcp-server@latest"],
    "env": {
      "FASTMCP_LOG_LEVEL": "ERROR",
      "AWS_DOCUMENTATION_PARTITION": "aws"
    }
  }
}

About this resource

Overview

AWS Documentation MCP Server is an official AWS Labs Model Context Protocol server that gives AI assistants structured access to AWS documentation. Instead of pasting AWS docs into a prompt, Claude can search the official AWS documentation, fetch a specific page and convert it to markdown, read individual sections, and get recommendations for related pages.

It runs locally over stdio via uvx from the published awslabs.aws-documentation-mcp-server Python package and needs no AWS account or credentials — it only reads public AWS documentation.

Features

  • Search documentation — query the official AWS documentation search API (available in the global aws partition).
  • Read documentation — fetch an AWS documentation page and convert it to clean markdown for the model to consume.
  • Read sections — retrieve specific sections of a documentation page rather than the whole article.
  • Recommendations — get content recommendations for related AWS documentation pages (global partition).
  • Available services list — list AWS services available in China regions (when using the aws-cn partition).

Use Cases

  • Ask Claude to find the AWS docs for a service or feature and summarize them.
  • Pull the current syntax for a CloudFormation resource or CLI command straight from the source docs.
  • Resolve "which AWS service does X" questions with citations to official pages.
  • Keep answers grounded in up-to-date AWS documentation instead of stale model knowledge.

Installation

Claude Code

  1. Ensure Python 3.10+ and uv are installed.
  2. Add the server with the stdio configuration shown above (command uvx, package awslabs.aws-documentation-mcp-server@latest).
  3. Verify it is connected with claude mcp list.

Claude Desktop / Cursor / Kiro / VS Code

Add the configSnippet above to your client's MCP configuration. The first run downloads the package via uvx; set AWS_DOCUMENTATION_PARTITION to aws for global documentation or aws-cn for the China partition.

Partitions

The AWS_DOCUMENTATION_PARTITION environment variable controls which AWS documentation partition the server targets. The default aws (global) partition exposes search, read, and recommendation tools; the aws-cn partition instead exposes a "get available services" listing. Tool availability differs between partitions, so pick the one that matches the regions you work in.

Source And Trust

This entry is based on the official AWS Labs awslabs/mcp repository and the published PyPI package. The server is read-only over public documentation, takes no AWS credentials, and is licensed Apache-2.0. Verify the package and configuration against the linked source before relying on it in automated workflows.

Source citations

Add this badge to your README

Show that AWS Documentation MCP Server is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.

Listed on HeyClaude
[![Listed on HeyClaude](https://heyclau.de/badge/mcp/aws-documentation-mcp-server.svg)](https://heyclau.de/entry/mcp/aws-documentation-mcp-server)

How it compares

AWS Documentation MCP Server side by side with 2 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.

Field

Official AWS Labs MCP server that lets AI assistants read, search, and get recommendations across AWS documentation, returning pages as clean markdown with no AWS account or credentials required.

Open dossier

Context7 MCP server by Upstash that pulls up-to-date, version-specific library documentation and code examples directly into Claude's context so answers match the libraries you actually use.

Open dossier

Official Microsoft Learn remote MCP server that gives AI agents real-time access to Microsoft documentation search, page fetch, and code sample search.

Open dossier
Trust
Install riskReview firstReview firstReview first
Notes Safety Privacy Safety Privacy Safety Privacy
BrandAWS Labs logoAWS LabsMicrosoft logoMicrosoft
Categorymcpmcpmcp
Sourcesource-backedsource-backedsource-backed
AuthorAWS LabsUpstashMicrosoft
Added2026-06-202026-06-022026-06-05
Platforms
Claude CodeCodexCursorClaude Desktop
Claude CodeClaude Desktop
Claude CodeClaude Desktop
Source repo
Safety notesThe server is read-only: it fetches and searches public AWS documentation and does not call AWS service APIs or modify any AWS resources. It requires no AWS account or credentials; do not add AWS access keys for this server. `AWS_DOCUMENTATION_PARTITION` selects the docs partition (`aws` global, or `aws-cn` for China); the available tools differ between partitions.Makes outbound network requests to the Context7 service to resolve libraries and fetch documentation. Returned documentation and code snippets are third-party content; review examples before running them in your project.The server is documentation-focused, but retrieved docs can still influence generated commands; review commands before running them. Remote MCP availability and schema can change, so verify client compatibility before depending on it in automation.
Privacy notesDocumentation URLs and search terms you ask about are sent to the official AWS documentation search/read endpoints to retrieve content. The server fetches public documentation pages over HTTPS and returns them as markdown; no private account data is read.The library names and documentation topics you query are sent to the Context7 service to return matching docs. Avoid placing secrets or private identifiers in the library queries passed to the server.Prompts and queries sent to a remote MCP server can reveal product names, architecture details, or error messages. Avoid sending customer identifiers or private tenant data when documentation search is enough.
Prerequisites
  • Python 3.10 or newer installed.
  • `uv` / `uvx` installed (Astral) to run the published Python package.
  • An MCP client that supports stdio servers (Claude Code, Claude Desktop, Cursor, Kiro, or VS Code).
  • Outbound HTTPS access so the server can fetch and search AWS documentation.
  • Node.js 18+ and npx available (verify with: npx --version)
  • Claude Code or Claude Desktop with MCP support
  • Internet access so the server can reach the Context7 documentation service
  • Optional Context7 API key for higher rate limits; the server also works without one
  • An MCP-compatible client that supports remote HTTP MCP servers.
  • Network access to learn.microsoft.com.
  • A Microsoft technology question where official Learn grounding is useful.
Install
uvx awslabs.aws-documentation-mcp-server@latest
claude mcp add context7 -- npx -y @upstash/context7-mcp
claude mcp add --transport http microsoft-learn https://learn.microsoft.com/api/mcp
Config
{
  "mcpServers": {
    "awslabs.aws-documentation-mcp-server": {
      "command": "uvx",
      "args": ["awslabs.aws-documentation-mcp-server@latest"],
      "env": {
        "FASTMCP_LOG_LEVEL": "ERROR",
        "AWS_DOCUMENTATION_PARTITION": "aws"
      },
      "type": "stdio"
    }
  }
}
{
  "mcpServers": {
    "context7": {
      "command": "npx",
      "args": [
        "-y",
        "@upstash/context7-mcp"
      ],
      "type": "stdio"
    }
  }
}
{
  "mcpServers": {
    "microsoft-learn": {
      "url": "https://learn.microsoft.com/api/mcp"
    }
  }
}
Citations
ClaimUnclaimedUnclaimedUnclaimed

Related guides

Signals

Loading live community signals…

More like this, weekly

A short, calm digest of reviewed Claude resources. Unsubscribe any time.