What is AWS Documentation?

AWS Documentation is an MCP (Model Context Protocol) server designed to fetch, convert, and search AWS documentation, while also providing recommendations for related content. It allows users to easily access and navigate AWS's extensive documentation and receive AI-powered suggestions for further reading.

How to use AWS Documentation?

1. Installation: Use uv (Astral's tool) or Docker to install and set up the MCP server.
2. Configuration: Add the server configuration to your MCP client (e.g., edit ~/.aws/amazonq/mcp.json).
3. Basic Usage: Query documentation or recommendations using natural language commands (e.g., "look up documentation on S3 bucket naming rules").
4. Tools: Utilize functions like read_documentation, search_documentation, recommend, and get_available_services (China-specific).

Key Features of AWS Documentation?

• Read Documentation: Convert AWS docs into markdown format.
• Search Documentation: Use global search API to find docs.
• Recommendations: Get AI-suggested related content (global only).
• China-Specific Services: List available AWS services in China regions.

Use Cases of AWS Documentation?

1. Quick Reference: Fetch documentation for specific AWS services (e.g., S3 rules).
2. Advanced Search: Query documentation using keywords or phrases.
3. AI Recommendations: Discover related content for deeper learning.
4. China Region Support: Verify available services in AWS China regions.

FAQ from AWS Documentation?

• Is this free to use?

  Yes, the MCP server is open-source and free to integrate.

• Can it fetch regional AWS documentation?

  Yes, set AWS_DOCUMENTATION_PARTITION=aws-cn for China-specific docs.

• Does it support translation?

  Not natively, but markdown output can be processed for translations.

AWS Documentation MCP Server

Model Context Protocol (MCP) server for AWS Documentation

This MCP server provides tools to access AWS documentation, search for content, and get recommendations.

Features

• Read Documentation: Fetch and convert AWS documentation pages to markdown format
• Search Documentation: Search AWS documentation using the official search API (global only)
• Recommendations: Get content recommendations for AWS documentation pages (global only)
• Get Available Services List: Get a list of available AWS services in China regions (China only)

Prerequisites

Installation Requirements

1. Install uv from Astral or the GitHub README
2. Install Python 3.10 or newer using uv python install 3.10 (or a more recent version)

Installation

Configure the MCP server in your MCP client configuration (e.g., for Amazon Q Developer CLI, edit ~/.aws/amazonq/mcp.json):

{
  "mcpServers": {
    "awslabs.aws-documentation-mcp-server": {
      "command": "uvx",
      "args": ["awslabs.aws-documentation-mcp-server@latest"],
      "env": {
        "FASTMCP_LOG_LEVEL": "ERROR",
        "AWS_DOCUMENTATION_PARTITION": "aws"
      },
      "disabled": false,
      "autoApprove": []
    }
  }
}

Note: Set AWS_DOCUMENTATION_PARTITION to aws-cn to query AWS China documentation instead of global AWS documentation.

or docker after a successful docker build -t mcp/aws-documentation .:

{
  "mcpServers": {
    "awslabs.aws-documentation-mcp-server": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "--interactive",
        "--env",
        "FASTMCP_LOG_LEVEL=ERROR",
        "--env",
        "AWS_DOCUMENTATION_PARTITION=aws",
        "mcp/aws-documentation:latest"
      ],
      "env": {},
      "disabled": false,
      "autoApprove": []
    }
  }
}

Basic Usage

Example:

• "look up documentation on S3 bucket naming rule. cite your sources"
• "recommend content for page https://docs.aws.amazon.com/AmazonS3/latest/userguide/bucketnamingrules.html"

Tools

read_documentation

Fetches an AWS documentation page and converts it to markdown format.

read_documentation(url: str) -> str

search_documentation (global only)

Searches AWS documentation using the official AWS Documentation Search API.

search_documentation(search_phrase: str, limit: int) -> list[dict]

recommend (global only)

Gets content recommendations for an AWS documentation page.

recommend(url: str) -> list[dict]

get_available_services (China only)

Gets a list of available AWS services in China regions.

get_available_services() -> str