A Model Context Protocol (MCP) server for Amazon S3 and S3-compatible object storage, enabling AI assistants to browse buckets, read and write objects, and generate presigned URLs.
Drift inferred · capture-to-capture
No drift recorded — single capability capture; advisories appear once its surface changes.
transport stdio counts 9 tools · 0 res
· 0 prompts
permission surface via README inference
tools
-
s3_copy_object
Copy object within/between buckets
-
s3_delete_object
Delete object (disabled in read-only mode)
-
s3_get_object
Retrieve object content
-
s3_get_object_metadata
Get object metadata without content
-
s3_list_buckets
List all accessible S3 buckets
-
s3_list_connections
List configured S3 connections
-
s3_list_objects
List objects with prefix/delimiter/pagination
-
s3_presign_url
Generate presigned GET/PUT URLs
-
s3_put_object
Upload object (disabled in read-only mode)
evidence-backed
findings quoted directly from the published source artifact — not inferred
This server hasn't been statically analyzed yet (npm/PyPI artifacts only).