AWS Documentation MCP server

AWS Documentation MCP server is a Model Context Protocol (MCP) implementation that provides tools to access, search, and get recommendations for AWS documentation. It enables you to interact with AWS documentation in an integrated way, allowing you to quickly look up information, search for specific content, and receive relevant recommendations.

Installation Prerequisites

Setting Up Dependencies

Before installing the MCP server, you need to:

1. Install uv from Astral or the GitHub repository
2. Install Python 3.10 or newer:

   uv python install 3.10
   

Configuration

You can configure the AWS Documentation MCP Server in different environments:

Using uvx (Recommended)

Create a configuration file (e.g., for Amazon Q Developer CLI MCP, at ~/.aws/amazonq/mcp.json):

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

Using Docker

First, build the Docker image:

docker build -t awslabs/aws-documentation-mcp-server .

Then configure the MCP server in your configuration file:

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

Usage

The AWS Documentation MCP Server provides several ways to interact with AWS documentation.

Basic Queries

You can ask natural language questions about AWS services, such as:

• "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"

Available Tools

Documentation Reader

The read_documentation tool fetches an AWS documentation page and converts it to markdown format.

read_documentation(url: str) -> str

Example:

content = read_documentation("https://docs.aws.amazon.com/AmazonS3/latest/userguide/bucketnamingrules.html")

Documentation Search

The search_documentation tool searches AWS documentation using the official AWS Documentation Search API.

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

Example:

results = search_documentation("S3 bucket lifecycle rules", 5)

Content Recommendations

The recommend tool gets content recommendations for an AWS documentation page.

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

Example:

recommendations = recommend("https://docs.aws.amazon.com/AmazonS3/latest/userguide/bucketnamingrules.html")

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.