Aerostack
Aerostack
electrical_services

AWS MCP Server — Hosted for Any AI Agent

MCP Server language Hosted language Public

List buckets, upload, download, delete, and manage objects in Amazon S3 — AI-native cloud storage access for any agent.

aerostack @aerostack verified
• v0.1.0 • MIT • Updated Jun 27, 2026
add_circleAdd to Workspace
robot_2

Use with AI AssistantsMCP

Connect Claude, Cursor, or any MCP-compatible client — then call tools directly

① Add This MCP Server

Paste into your AI client config — then all its tools are available instantly.

.claude/mcp.json
{
  "mcpServers": {
    "aws-s3": {
      "url": "https://mcp.aerostack.dev/s/aerostack/mcp-aws-s3",
      "headers": {
        "Authorization": "Bearer YOUR_AEROSTACK_TOKEN"
      }
    }
  }
}

Replace YOUR_AEROSTACK_TOKEN with your API token from the dashboard.

② Call a Tool

Ask your AI assistant to call a specific tool, or send raw JSON-RPC:

+4 more

Natural Language Prompt

“Use the _ping tool to verify aws s3 connectivity by listing buckets. used internally by aerostack to validate credentials”

Using a Workspace?

Add this MCP to your Workspace — your team shares one token, secrets are stored securely, and every AI agent in the workspace can call it without per-user setup.

add_circleAdd to Workspace

description Overview

mcp-aws-s3 — AWS S3 MCP Server

List buckets, upload, download, delete, and manage objects in Amazon S3 — AI-native cloud storage access for any agent.

Live endpoint: https://mcp.aerostack.dev/s/aerostack/mcp-aws-s3

What You Can Do

This MCP server gives AI agents access to AWS S3 via 9 tools. Connect it to any Aerostack workspace and your agents can interact with AWS S3 directly.

Available Tools

Tool Description
list_buckets List all S3 buckets in the AWS account with name, region, and creation date
list_objects List objects in an S3 bucket with optional prefix filter, delimiter for folder-like navigation, and pagination
get_object Download an object from S3 and return its content as text. For binary files, returns a pre-signed download URL instead.
put_object Upload a text or JSON object to S3 with optional content type and metadata
delete_object Delete an object from an S3 bucket by key
copy_object Copy an object from one location to another within or across S3 buckets
head_object Get metadata for an S3 object without downloading it — size, content type, last modified, ETag, and custom metadata
presign_url Generate a pre-signed URL for temporary access to an S3 object (upload or download) without sharing credentials
create_bucket Create a new S3 bucket in the configured AWS region

Configuration

Variable Required Description
AWS_ACCESS_KEY_ID Yes See provider documentation
AWS_SECRET_ACCESS_KEY Yes Secret key from the provider's developer console
AWS_REGION Yes See provider documentation

Quick Start

Add to Aerostack Workspace
  1. Go to aerostack.dev → Your Project → MCPs
  2. Search for "AWS S3" and click Add to Workspace

Add the following secrets under Project → Secrets:

  • AWS_ACCESS_KEY_ID
  • AWS_SECRET_ACCESS_KEY
  • AWS_REGION

Once added, every AI agent in your workspace can use AWS S3 tools automatically.

Direct API Call
curl -X POST https://mcp.aerostack.dev/s/aerostack/mcp-aws-s3 \
  -H 'Content-Type: application/json' \
  -H 'X-Mcp-Secret-AWS-ACCESS-KEY-ID: your-aws-access-key-id' \
  -H 'X-Mcp-Secret-AWS-SECRET-ACCESS-KEY: your-aws-secret-access-key' \
  -H 'X-Mcp-Secret-AWS-REGION: your-aws-region' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"list_buckets","arguments":{}}}'

License

MIT

terminal Tools (10)

Available tools on this MCP server. Each tool can be called directly from any AI agent.

terminal
_ping #1

Verify AWS S3 connectivity by listing buckets. Used internally by Aerostack to validate credentials.

terminal
list_buckets #2

List all S3 buckets in the AWS account with name, region, and creation date

terminal
list_objects #3

List objects in an S3 bucket with optional prefix filter, delimiter for folder-like navigation, and pagination

terminal
get_object #4

Download an object from S3 and return its content as text. For binary files, returns a pre-signed download URL instead.

terminal
put_object #5

Upload a text or JSON object to S3 with optional content type and metadata

terminal
delete_object #6

Delete an object from an S3 bucket by key

terminal
copy_object #7

Copy an object from one location to another within or across S3 buckets

terminal
head_object #8

Get metadata for an S3 object without downloading it — size, content type, last modified, ETag, and custom metadata

terminal
presign_url #9

Generate a pre-signed URL for temporary access to an S3 object (upload or download) without sharing credentials

terminal
create_bucket #10

Create a new S3 bucket in the configured AWS region

Details

upgrade Version 0.1.0
gavel License MIT
wifi Transport streamable-http
lock Access Public
category Category Devops
terminal Tools 10

language Live Endpoint

https://mcp.aerostack.dev/s/aerostack/mcp-aws-s3

Sub-50ms globally · Zero cold start

Publisher

aerostack
@aerostack verified

Pre-built functions for the most common MCP tool patterns. Clone, extend, and deploy.

Tags

aws s3 cloud storage files buckets
Browse more servers

More in Devops

Browse Devops MCPs →
hub

Asana Project Management

by @aerostack

Tasks, projects, sections, comments, teams, custom fields via Asana's official MCP

devops
star 0
hub

Atlassian Cloud

by @aerostack

Jira issues, sprints, Confluence pages via Atlassian's official MCP

devops
star 0
hub

Cloudflare Platform

by @aerostack

Cloudflare Workers, KV, R2, D1, Pages, DNS via Cloudflare's official MCP

devops
star 0
hub

Datadog Observability

by @aerostack

Dashboards, monitors, logs, metrics, incidents, SLOs, APM traces via Datadog's official MCP

devops
star 0
hub

Figma Design

by @aerostack

Files, frames, components, comments, variables via Figma's official MCP

devops
star 0
hub

GitHub API

by @aerostack

GitHub repos, PRs, issues, branches, code search via GitHub's official hosted MCP

devops
star 0

Frequently asked questions

What is the AWS MCP server and what can it do? +

The AWS MCP server is hosted on Aerostack and exposes these tools to your AI agent: `_ping`, `list_buckets`, `list_objects`, `get_object`, `put_object`. You get one hosted URL — no self-hosting — that works from Claude, Cursor, ChatGPT, Gemini, VS Code, or any MCP-compatible client, and you can share it with your team or combine it with other MCP servers in a workspace.

Is the AWS MCP server hosted, or do I have to run it myself? +

It's hosted on Aerostack's edge infrastructure — you don't deploy or maintain anything. Add it to a workspace and you get one authenticated URL, with secrets encrypted, that any AI agent or editor can connect to. Use it solo or share the same URL across your whole team.

Which AI agents and editors can use the AWS MCP server? +

Any MCP client: Claude and Claude Code, Cursor, ChatGPT, Gemini, Windsurf, Cline, VS Code, and custom agents. Because it's one hosted URL, the same AWS MCP server works everywhere — and you can compose it with other MCP servers, skills, and functions behind a single workspace URL.

How do I install the AWS MCP server in Claude Desktop? +

Add the following to your Claude Desktop config (`claude_desktop_config.json`): ```json { "mcpServers": { "@aerostack/mcp-aws-s3": { "command": "npx", "args": ["-y", "@aerostack/@aerostack/mcp-aws-s3"] } } } ``` Then restart Claude Desktop and the tools will appear automatically.

How do I use the AWS MCP server in Cursor? +

In Cursor, open **Settings → MCP** and add: ```json { "name": "@aerostack/mcp-aws-s3", "command": "npx", "args": ["-y", "@aerostack/@aerostack/mcp-aws-s3"] } ``` Save and reload Cursor. The MCP tools will be available in Agent mode.

Does AWS MCP require authentication? +

Yes. AWS requires authentication. Check the MCP's documentation for the required credentials.