S3 MCP Server

v1.0.0File Systemsstable

Enables interaction with AWS S3 buckets to list buckets and objects, retrieve files, and expose PDF documents as resources that can be loaded into the LLM's context.

sample-s3-mcp-servermcpai-integration
Share:
79
Stars
0
Downloads
0
Weekly
0/5

What is S3 MCP Server?

S3 MCP Server is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to enables interaction with aws s3 buckets to list buckets and objects, retrieve files, and expose pdf documents as resources that can be loaded into the llm's context.

Enables interaction with AWS S3 buckets to list buckets and objects, retrieve files, and expose PDF documents as resources that can be loaded into the LLM's context.

This server falls under the File Systems and Cloud Services categories on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Enables interaction with AWS S3 buckets to list buckets and

Use Cases

Interact with AWS S3 buckets for file management.
Extract and load PDF documents into AI context.
aws-samples

Maintainer

LicenseMIT No Attribution
Languagepython
Versionv1.0.0
UpdatedApr 25, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx sample-s3-mcp-server

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use S3 MCP Server

The Sample S3 MCP Server is an AWS-provided reference implementation that connects AI assistants to Amazon S3 through the Model Context Protocol, enabling them to list buckets, enumerate objects, retrieve files, and load PDF documents directly into the LLM's context as resources. Built with the Python MCP SDK and the uvx distribution model, it exposes three core tools (ListBuckets, ListObjectsV2, GetObject) and treats S3-hosted PDF files as first-class MCP Resources so their content flows seamlessly into the conversation. Teams use it to give AI assistants direct read access to S3-hosted data, documentation, and reports without manual downloads.

Prerequisites

  • Python 3.10 or higher with uv installed (pip install uv)
  • An AWS account with S3 access and credentials (Access Key ID, Secret Access Key, and region)
  • IAM permissions for s3:ListAllMyBuckets, s3:ListBucket, and s3:GetObject on the target buckets
  • An MCP-compatible client such as Claude Desktop
1

Obtain AWS credentials with S3 permissions

In the AWS Management Console, go to IAM and create or locate a user with the AmazonS3ReadOnlyAccess policy (or a custom policy granting ListAllMyBuckets, ListBucket, and GetObject). Generate an access key and note the Access Key ID, Secret Access Key, and your target region.

2

Install uv if not already available

The server is distributed via uvx (part of the uv toolchain). Install uv first if you do not have it.

pip install uv
# or on macOS:
brew install uv
3

Test the server locally

Verify the server runs correctly by launching it with your AWS credentials set as environment variables.

AWS_ACCESS_KEY_ID=your-key-id \
AWS_SECRET_ACCESS_KEY=your-secret \
AWS_REGION=us-east-1 \
uvx s3-mcp-server
4

Configure Claude Desktop with your AWS credentials

Open the Claude Desktop config file (~/Library/Application Support/Claude/claude_desktop_config.json on macOS or %APPDATA%\Claude\claude_desktop_config.json on Windows) and add the S3 server entry with your credentials in the env block.

5

Restart Claude Desktop and test S3 access

Restart Claude Desktop. Ask it to list your S3 buckets to confirm the server is connected and credentials are working.

S3 MCP Server Examples

Client configuration

Add this to your claude_desktop_config.json. Replace the placeholder credential values with your actual AWS keys and preferred region.

{
  "mcpServers": {
    "s3-mcp-server": {
      "command": "uvx",
      "args": ["s3-mcp-server"],
      "env": {
        "AWS_ACCESS_KEY_ID": "AKIAIOSFODNN7EXAMPLE",
        "AWS_SECRET_ACCESS_KEY": "wJalrXUtnFEMI/K7MDENG/bPxRfiCYEXAMPLEKEY",
        "AWS_REGION": "us-east-1"
      }
    }
  }
}

Prompts to try

Use natural language to navigate and retrieve content from your S3 buckets.

- "List all my S3 buckets"
- "Show me the objects in the bucket named my-data-bucket"
- "Retrieve the file reports/q4-2024.pdf from my-data-bucket"
- "Load the PDF at s3://my-docs-bucket/manual.pdf into context and summarize it"

Troubleshooting S3 MCP Server

ListBuckets returns empty or AccessDenied error

Confirm the IAM user or role has the s3:ListAllMyBuckets permission. The credentials must belong to an AWS account that actually owns S3 buckets. Check with 'aws s3 ls' using the same credentials via the AWS CLI.

PDF content does not appear as a resource in Claude

The server only exposes PDF documents as MCP Resources, not arbitrary file types. Ensure the object key ends in .pdf. Also note the server is limited to 1,000 objects per ListObjectsV2 call — PDFs beyond that threshold may not be surfaced.

uvx s3-mcp-server fails with 'package not found'

The published package name is 's3-mcp-server'. Ensure uv is up to date ('pip install --upgrade uv'). If the published version is unavailable, clone the repo and use the development config: {"command": "uv", "args": ["--directory", "/path/to/sample-mcp-server-s3", "run", "s3-mcp-server"]}.

Frequently Asked Questions about S3 MCP Server

What is S3 MCP Server?

S3 MCP Server is a Model Context Protocol (MCP) server that enables interaction with aws s3 buckets to list buckets and objects, retrieve files, and expose pdf documents as resources that can be loaded into the llm's context. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install S3 MCP Server?

Follow the installation instructions on the S3 MCP Server GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with S3 MCP Server?

S3 MCP Server works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is S3 MCP Server free to use?

Yes, S3 MCP Server is open source and available under the MIT No Attribution license. You can use it freely in both personal and commercial projects.

Browse More File Systems MCP Servers

Explore all file systems servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "sample-s3-mcp-server": { "command": "npx", "args": ["-y", "sample-s3-mcp-server"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use S3 MCP Server?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides