What it does

This MCP server implementation extracts data, such as PDF files, from AWS S3 buckets. It provides access to S3 objects through resources and tools.

When to use - and when NOT to

Use this server when you need to provide access to data stored in AWS S3 buckets, particularly for PDF documents. It's suitable for scenarios where you want to expose S3 objects as GET endpoints. Do not use this if your data is not stored in AWS S3 or if you require support for file formats other than PDF, as only PDF document support is currently available.

Inputs and outputs

Inputs are implicitly AWS S3 buckets and objects, accessed via configured AWS credentials with READ/WRITE permissions. The server exposes S3 objects as resources, primarily supporting PDF documents. The ListObjectsV2 tool is limited to returning a maximum of 1000 objects per request.

Integrations

Integration with AWS S3 buckets.

Who it's for

This tool is for developers and AI engineers who need to integrate data from AWS S3.

Installation and Usage Examples:

Development/Unpublished Version:

uv --directory /Users/user/generative_ai/model_context_protocol/s3-mcp-server run s3-mcp-server

Published Version:

uvx s3-mcp-server

Building from Source:

uv sync
uv build
uv publish

Claude Desktop - Development Configuration:

{
  "mcpServers": {
    "s3-mcp-server": {
      "command": "uv",
      "args": [
        "--directory",
        "/Users/user/generative_ai/model_context_protocol/s3-mcp-server",
        "run",
        "s3-mcp-server"
      ]
    }
  }
}

Claude Desktop - Published Version Configuration:

{
  "mcpServers": {
    "s3-mcp-server": {
      "command": "uvx",
      "args": [
        "s3-mcp-server"
      ]
    }
  }
}