drio
Open app

S3 MCP Server

Source

MCP server to integrate AWS S3 and LLM

Catalog onlyCatalog onlySTDIO

Overview

S3 MCP Server is an Amazon S3 Model Context Protocol (MCP) server that enables Large Language Models (LLMs) to interact with AWS S3 storage, providing tools for managing S3 buckets and objects.

To use the S3 MCP Server, install it via npm, configure your AWS credentials, and run the server. You can then connect it to applications like Claude Desktop to perform S3 operations.

  • List available S3 buckets - List objects within a bucket - Retrieve object contents - Secure and standardized interface for LLMs to access S3
  1. Integrating LLMs with AWS S3 for data retrieval.
  2. Automating S3 bucket management tasks.
  3. Enabling natural language queries for S3 operations through LLMs.

Add to your AI client

Use these steps to connect S3 MCP Server in Cursor, Claude, VS Code, and other MCP-compatible apps. The same JSON appears in the Use with menu above for one-click copy.

Cursor

Add this to your .cursor/mcp.json file in your project root, then restart Cursor.

.cursor/mcp.json

{
  "mcpServers": {
    "aws-s3-mcp-samuraikun": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-aws-s3-mcp-samuraikun"
      ]
    }
  }
}

Claude Desktop

Add this server entry to the mcpServers object in your Claude Desktop config, then restart the app.

~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)

{
  "mcpServers": {
    "aws-s3-mcp-samuraikun": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-aws-s3-mcp-samuraikun"
      ]
    }
  }
}

Claude Code

Add this to your project's .mcp.json file. Claude Code will detect it automatically.

.mcp.json (project root)

{
  "mcpServers": {
    "aws-s3-mcp-samuraikun": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-aws-s3-mcp-samuraikun"
      ]
    }
  }
}

VS Code (Copilot)

Add this to your .vscode/mcp.json file. Requires the GitHub Copilot extension with MCP support enabled.

.vscode/mcp.json

{
  "servers": {
    "aws-s3-mcp-samuraikun": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-aws-s3-mcp-samuraikun"
      ]
    }
  }
}

Windsurf

Add this to your Windsurf MCP config file, then restart Windsurf.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "aws-s3-mcp-samuraikun": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-aws-s3-mcp-samuraikun"
      ]
    }
  }
}

Cline

Open Cline settings, navigate to MCP Servers, and add this server configuration.

Cline MCP Settings (via UI)

{
  "mcpServers": {
    "aws-s3-mcp-samuraikun": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/server-aws-s3-mcp-samuraikun"
      ]
    }
  }
}

FAQ

What are the prerequisites for using S3 MCP Server?

Node.js 18 or higher, npm or yarn, and configured AWS credentials are required.

Can I run S3 MCP Server locally?

Yes, you can run it locally after installation and configuration.

Is there a limit on the number of S3 buckets I can access?

Yes, you can configure a maximum number of buckets to return in the listing.

Cloud storage