Loading...
List buckets, browse objects, generate presigned URLs, and manage files via S3 REST API
35+ deploysYour AI agent gets 6 capabilities in one connection. Deploy once, use from any client.
GET endpoints
list_buckets
List all S3 buckets in the account. Returns bucket name, creation date, and region. Useful for discovering available storage before listing objects.
https://s3.{region}.amazonaws.com/
list_objects
List up to 50 objects in a bucket with optional prefix filter. Returns key, size, last modified, and storage class. Use prefix for folder-like navigation.
https://{bucket}.s3.{region}.amazonaws.com/?list-type=2&max-keys=50&prefix={prefix}
get_object
Download an object from S3 by its full key path. Returns the raw file content with Content-Type and metadata headers.
https://{bucket}.s3.{region}.amazonaws.com/{key}
PUT endpoints
put_object
Upload a file to S3 at the specified key. Set content_type to match the file (e.g., application/json, image/png). Overwrites if key exists.
https://{bucket}.s3.{region}.amazonaws.com/{key}
DELETE endpoints
delete_object
Permanently delete an object from S3 by key. No confirmation or trash — deletion is immediate and irreversible unless versioning is enabled.
https://{bucket}.s3.{region}.amazonaws.com/{key}
HEAD endpoints
head_object
Get object metadata without downloading the file. Returns Content-Length (bytes), Content-Type, Last-Modified, ETag, and x-amz-meta-* custom headers. Use to check existence (404 if missing) or verify upload.
https://{bucket}.s3.{region}.amazonaws.com/{key}
Connect AWS S3 to Claude Code with one command:
claude mcp add aws_s3 https://datafaucet.dev/api/mcp/t/aws-s3{notion_token}) with your real credentialsNeed API keys? Try our free sandbox templates first to see MCP in action with zero setup.
Replace these placeholders with your real values before deploying:
{aws_access_key}Your value{bucket}Your value{content_type}Your value{date}Your value{key}Your value{prefix}Your value{region}Your valuePreview:
GET https://s3.{region}.amazonaws.com/ Authorization: AWS4-HMAC-SHA256 Credential={aws_access_key}/{date}/{region}/s3/aws4_request
claude mcp add aws_s3 --url https://datafaucet.dev/api/mcp/t/aws-s3
Paste into your client's MCP configuration file · most users connect in under 60s
claude mcp add aws_s3 --url https://datafaucet.dev/api/mcp/t/aws-s3What your AI agent sees
I have access to 6 tools from AWS S3: list_buckets, list_objects, get_object, and 3 more.
“List all S3 buckets in the account. Returns bucket name, creation date, and region. Useful for discovering available storage before listing objects.”
Calling list_buckets... Done. Here are the results.
Try these prompts
“List all S3 buckets in the account. Returns bucket name, creation date, and region. Useful for discovering available storage before listing objects”
Copy“List up to 50 objects in a bucket with optional prefix filter. Returns key, size, last modified, and storage class. Use prefix for folder-like navigation”
Copy“Download an object from S3 by its full key path. Returns the raw file content with Content-Type and metadata headers”
CopyClick any prompt to copy, then paste into your AI client.