aws-s3-mcp
MCP server to integrate AWS S3 and LLM
No outside reports on file
Use this tool only with narrow AWS permissions, restricted to specific S3 buckets you fully control, and monitor what data the AI accesses.
Based on public adoption and transparency signals as of Oct 22, 2026. Our opinion, not a code audit or security guarantee.
What it can access
- Local filesNo local folder access notedLOW
- Command executionNo shell command runner notedLOW
- Network reachConnects to outside service APINOTED
- CredentialsRequires API key or tokenREVIEW
- Package sourcenpm (aws-s3-mcp)PUBLIC
Inferred from this listing’s public package details and description. Check the project’s source before installing.
Install
npx -y aws-s3-mcpAbout AWS S3 MCP
This is a connector that lets AI language models (like Claude) read files from and write files to Amazon S3 cloud storage. It acts as a bridge so the AI can access your S3 buckets directly through the MCP (Model Context Protocol) system.
Who it’s for
Developers who want their AI assistants to work with files stored in AWS S3, such as processing documents, retrieving data, or automating file management tasks. It's useful for teams already using AWS and Claude together.
Alternatives
- AWS Lambda + Claude API: Call Lambda functions from Claude to interact with S3 (more complex but finer control).
- Direct S3 CLI: Have Claude guide you through AWS CLI commands rather than granting direct access.
- Azure Blob Storage connector: If you use Microsoft Azure instead of AWS, similar tools exist for that platform.
- Local file system MCP: If your data doesn't need to be in the cloud, use file access restricted to a local folder instead.
Setup
Check these steps against the project’s own instructions before running anything.
Install via npm with: npm install -g aws-s3-mcp
Or add to Claude Desktop by updating your config file with the GitHub repository details. Follow the project's README for authentication setup (you'll need AWS credentials configured on your system).
Why this grade
Signal-based grade (2/7 points): listed in several sources, public source code. This reflects adoption and transparency, not a code review.
Popularity and upkeep
- GitHub stars
- 30
- Weekly npm downloads
- 8k
- Listing last refreshed
- 2026-10-29
These are public popularity signals, not a maintenance check. Look at the repository’s commit history and open issues.
Security reports
No reports found for this package in our research (last checked 2026-10-29).
Risks to watch for
- AWS account access: The connector can read and modify any S3 files the AWS credentials allow, so overly permissive credentials could expose large amounts of data.
- Credential leakage: AWS access keys stored on your system could be extracted if your computer is compromised.
- Malicious file content: S3 files containing specially crafted prompts or code could trick the AI into dangerous behavior.
- Unintended data exposure: The AI might summarize, copy, or process sensitive files without clear limits on what buckets it can touch.
- Large data transfers: Running this against huge S3 buckets could cost money or slow down your system.
How to lower the risk
Least-privilege permissions
- Create an AWS user with permissions only for the specific S3 buckets and operations needed.
- Never use your main AWS account credentials; use a separate role with minimal access.
Network isolation
- Run this on a trusted machine, ideally not open to the internet.
- Keep AWS credentials in environment variables, not in code or config files.
Monitoring
- Enable AWS CloudTrail to log all S3 file access.
- Regularly audit which files the AI has accessed and why.
Red flags to watch for
- Sudden access to S3 buckets you didn't intend to expose.
- Attempts to list or access buckets outside your approved scope.
- Large downloads or unexpected data transfers incurring costs.
Questions
How do I install AWS S3 MCP?
Run npx -y aws-s3-mcp in your terminal, or add the server entry to your claude_desktop_config.json or .cursor/mcp.json as shown in the Setup section on this page. Full setup docs and environment variables are in github.com/samuraikun/aws-s3-mcp.
Are there security reports about AWS S3 MCP?
No reports found for this package in our research (last checked 2026-10-29). AWS S3 MCP currently holds Grade C (Moderate risk signals) based on public adoption and transparency signals. Key risk areas to watch include aws account access, credential leakage, malicious file content.
Is AWS S3 MCP actively maintained?
AWS S3 MCP has 30 GitHub stars and 8k weekly npm downloads. Our directory data was last refreshed on 2026-10-29. Check recent commit activity, release tags, and open issues at github.com/samuraikun/aws-s3-mcp before pinning it in production.
What are alternatives to AWS S3 MCP?
Notable alternatives to AWS S3 MCP include AWS Lambda + Claude API (Call Lambda functions from Claude to interact with S3 (more complex but finer control)), Direct S3 CLI (Have Claude guide you through AWS CLI commands rather than granting direct access), Azure Blob Storage connector (If you use Microsoft Azure instead of AWS, similar tools exist for that platform), Local file system MCP (If your data doesn't need to be in the cloud, use file access restricted to a local folder instead). You can also compare AWS S3 MCP side by side with other MCP servers in the Related tools section on this page.
README badge and team notes
Maintain or use AWS S3 MCP? Show its live grade in your GitHub README, docs site, or run a check from the terminal before you install.
GitHub README Markdown:
[](https://agentarmorhq.com/skills/samuraikun-aws-s3-mcp)HTML embed:
<a href="https://agentarmorhq.com/skills/samuraikun-aws-s3-mcp"><img src="https://agentarmorhq.com/api/badge/samuraikun-aws-s3-mcp" alt="AgentArmorHQ Risk Grade for AWS S3 MCP" height="20" /></a>Terminal check:
curl -fsSL https://agentarmorhq.com/api/cli | node --input-type=module - check "samuraikun-aws-s3-mcp"Share with your security lead
Need sign-off to use aws-s3-mcp? Copy this note for Slack, a ticket or a pull request.
### AgentArmorHQ Security Review Memo: aws-s3-mcp
- **Listing URL:** https://agentarmorhq.com/skills/samuraikun-aws-s3-mcp
- **Type:** App connector
- **Risk Grade:** Grade C (Moderate risk signals)
- **Outside Security Advisories on File:** 0
- **Public Adoption:** 30 GitHub stars, 8k weekly npm downloads
#### Permission & Blast-Radius Signals
- **Local files:** No local folder access noted
- **Command execution:** No shell command runner noted
- **Network reach:** Connects to outside service API
- **Credentials:** Requires API key or token
- **Package source:** npm (aws-s3-mcp)
#### Recommended Hardened Setup
- **Command:** `npx -y --ignore-scripts aws-s3-mcp`
- **Controls:** Pin an exact version in `.mcp.json`, scope access to a single workspace folder, and use a least-privilege read-only token where supported.
_Based on public adoption and transparency signals as of Oct 22, 2026. Our opinion, not a code audit or security guarantee._Key facts
- Type
- App connector
- Publisher
- samuraikun
- Source code
- github.com/samuraikun/aws-s3-mcp
- Install command
- npm install aws-s3-mcp
- Est. context load
- ~650 tokens / turn (~4 tool schemas, 0.33% of 200k context)
- Popularity
- 30 GitHub stars, 8k weekly npm downloads
- Last updated
- 2026-10-29
- Last graded
- 2026-10-22
Community
Discussions for AWS S3 MCP
Ask questions or share configuration tips. Governed by our Community Rules & Terms.
No posts match this filter yet.
Be the first to ask a question or share a working tip.
Check before you install, in Claude
Your assistant answers Block, Review or No known issues for any package before it installs it.
Get this check inside Claude