S3 MCP Server

@ashgw

Repository

Basic information

About S3 MCP Server

Fully Loaded AWS S3 Model Context Protocol Server (MCP)

#s3-mcp#aws-s3 #server-management

S3 MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "s3-mcp": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "AWS_SECRET_ACCESS_KEY=your_access_key",
        "-e",
        "AWS_ACCESS_KEY_ID=your_access_key",
        "-e",
        "AWS_REGION=your_region",
        "ashgw/s3-mcp:latest"
      ]
    }
  }
}

S3 MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is S3 Mcp?

S3 Mcp is a Model Context Protocol server that enables AI assistants to manage Amazon S3 buckets and objects directly. It provides tools for bucket and object operations, lifecycle policies, tagging, CORS configuration, and more. It is intended for developers who want to integrate S3 management into AI-driven workflows.

How to use S3 Mcp?

S3 Mcp can be run via Docker with AWS credentials passed as environment variables. It can be configured in Cursor by adding a Docker-based MCP server entry to the Cursor MCP configuration. Manual Docker execution is also supported, and the server can be built from the repository.

Key features of S3 Mcp

List, create, and delete S3 buckets
List, get, put, delete, and copy objects
Generate presigned URLs for objects
Manage bucket policies (set, get, delete)
Configure lifecycle rules and CORS
Set and retrieve object tags
Upload local files and download to local path

Use cases of S3 Mcp

List all S3 buckets from an AI chat interface
Create a new bucket with versioning and encryption enabled
Upload a local file to an S3 bucket
Retrieve object tags for a specific file
Generate a presigned URL for temporary object access

Frequently asked questions

What runtime or dependencies are required?

Docker is required to run the pre-built image or to build the server from source. AWS credentials must be provided via environment variables.

How are AWS credentials supplied?

Credentials are passed as `AWS_ACCESS_KEY_ID`, `AWS_SECRET_ACCESS_KEY`, and `AWS_REGION` environment variables when running the container.

Where does the data live?

All data operations are performed directly on Amazon S3. The server itself does not store any persistent data.

What transports are supported?

The server uses standard input/output (stdio) communication, as typical for MCP servers run via Docker.

Is the server authenticated?

Authentication is handled via the provided AWS credentials, not through a separate MCP-level auth mechanism.

Comments

More Files & Storage MCP servers

PDF Reader MCP Server (@sylphlab/pdf-reader-mcp)

sylphlab

📄 The PDF intelligence layer for AI agents — Agent Document Twin, evidence-first extraction, visual crops, OCR provenance, trust reports, and benchmark-gated releases. MCP server for Claude, Cursor, VS Code, and any MCP client.

810