AWS S3 MCP Server
Manage AWS S3 operations, providing secure access to S3 buckets through pre-signed URLs.
AWS S3 MCP Server
MCP Server for AWS S3 operations, providing secure access to S3 buckets through pre-signed URLs.
Tools
-
list_objects- List objects in an S3 bucket
- Input:
prefix(string, optional): Prefix filter for object keys
- Returns: Array of objects with keys, sizes, and last modified dates
-
get_object- Generate a pre-signed URL for accessing an object
- Inputs:
key(string, required): Object key to retrieveexpiry(number, optional): URL expiration time in seconds (default: 3600)
- Returns:
object_urlcontaining the pre-signed URL
-
put_object- Generate a pre-signed URL for uploading an object
- Inputs:
key(string, required): Object key to uploadexpiry(number, optional): URL expiration time in seconds (default: 3600)
- Returns:
upload_urlcontaining the pre-signed URL
-
delete_object- Delete an object from the bucket
- Input:
key(string, required): Object key to delete
- Returns:
successboolean indicating deletion status
Setup
Environment Variables
The server requires the following environment variables:
BUCKET_NAME: The name of your S3 bucket (required)REGION: AWS region (default: "ap-southeast-1")
AWS credentials should be configured using standard AWS credential configuration methods (environment variables, IAM roles, or AWS credentials file).
Usage with Claude Desktop
Add the following to your claude_desktop_config.json:
{
"mcpServers": {
"aws-ow-s3-mcp": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"-e",
"BUCKET_NAME",
"-e",
"REGION",
"-e",
"AWS_ACCESS_KEY_ID",
"-e",
"AWS_SECRET_ACCESS_KEY",
"mcp/aws-ow-s3-mcp"
],
"env": {
"BUCKET_NAME": "<YOUR_BUCKET_NAME>",
"REGION": "<AWS_REGION>",
"AWS_ACCESS_KEY_ID": "<YOUR_ACCESS_KEY>",
"AWS_SECRET_ACCESS_KEY": "<YOUR_SECRET_KEY>"
}
}
}
}
NPX Command
{
"mcpServers": {
"aws-ow-s3-mcp": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-aws-ow-s3-mcp"
],
"env": {
"BUCKET_NAME": "<YOUR_BUCKET_NAME>",
"REGION": "<AWS_REGION>",
"AWS_ACCESS_KEY_ID": "<YOUR_ACCESS_KEY>",
"AWS_SECRET_ACCESS_KEY": "<YOUR_SECRET_KEY>"
}
}
}
}
Build
Docker build:
docker build -t mcp/aws-ow-s3-mcp-server .
Development
The server is built using:
- Node.js
- TypeScript
- @modelcontextprotocol/sdk
- @aws-sdk/client-s3
- @aws-sdk/s3-request-presigner
License
This MCP server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.
Похожие серверы
Google Photos
Access and manage your Google Photos library with AI assistants.
Apache OpenDAL™
Access various storage services like S3, GCS, and Azure Blob through the Apache OpenDAL™ project, configured via environment variables.
AWS S3
Retrieve files like PDFs from an AWS S3 bucket. Requires AWS credentials for access.
Hindsight
Hindsight: Agent Memory That Works Like Human Memory
Intersight MCP
A comprehensive MCP server for configuring and managing Cisco Intersight.
MCP IPFS Server
Interact with the storacha.network IPFS platform using the w3 CLI.
Memory Bank MCP
An MCP server for remote memory bank management, enhanced with Supergateway for streamable-http transport. It supports multi-project management and requires persistent storage.
VaultSage MCP
Give your AI agent persistent memory: upload, search, and chat over files stored in VaultSage — no install required, just sign in with Google and paste one token.
Qiniu MCP Server
Access Qiniu's cloud storage, intelligent multimedia services, and CDN operations via the Model Context Protocol.
CData IBM Cloud Object Storage
A read-only MCP server for IBM Cloud Object Storage, powered by CData. Requires a separate CData JDBC Driver license.