Sample MCP Server S3

🚀 S3 Model Context Protocol Server Example

An MCP server implementation for retrieving data (such as PDF files) from S3.

🚀 Quick Start

This is an MCP server implementation designed to fetch data, like PDF files, from AWS S3. It provides various features and tools to interact with S3 resources.

✨ Features

Resources

Display AWS S3 data through Resources (similar to GET endpoints; they are used to load information into the LLM's context). Currently, only PDF files are supported, and a maximum of 1000 objects are displayed.

Tools

• ListBuckets
  • Returns a list of all buckets owned by the authenticated request sender.
• ListObjectsV2
  • Returns some or all (up to 1000 per request) objects in a bucket.
• GetObject
  • Retrieves an object from Amazon S3. In the GetObject request, specify the full key name of the object. It supports both virtual-hosted–style requests and path-style requests for general buckets.

📦 Installation

Set AWS Credentials

1. Obtain the AWS access key ID, secret access key, and region through the AWS Management Console. Configure the credentials file using the default profile, as shown here.
2. Ensure that these credentials have appropriate permissions to read/write to S3.

Use with Claude Desktop

Windows and MacOS

On MacOS: ~/Library/Application\ 支持/Claude/claude_desktop_config.json On Windows: %APPDATA%/Claude/claude_desktop_config.json%

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

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

💻 Usage Examples

Build and Release

To prepare the distribution package:

# Synchronize dependencies and update the lock file
uv sync

# Build the release version
uv build

This will create source and wheel distributions in the dist/ directory.

# Publish to PyPI
uv publish

Note: You need to set your PyPI credentials through environment variables or command-line parameters:

• Token: --token or UV_PUBLISH_TOKEN
• Or username/password: --username / UV_PUBLISH_USERNAME and --password / UV_PUBLISH_PASSWORD

Debugging

Since the MCP server runs through standard input and output, debugging can be challenging. For the best debugging experience, we highly recommend using the MCP Inspector.

You can start the MCP Inspector by executing the following command with npm:

npx @modelcontextprotocol/inspector uv --directory /Users/user/generative_ai/model_context_protocol/s3-mcp-server run s3-mcp-server

After starting, the inspector will display a URL that you can access in your browser to start debugging.

🔧 Technical Details

Security

For more information, please refer to CONTRIBUTING

📄 License

MIT License

All rights reserved. Please review the full license information.