Connect to an AWS S3 bucket. Supports two modes:

1. Credentials mode (private buckets): provide aws_access_key_id + aws_secret_access_key + region_name.

2. Public mode (no credentials): provide s3_url only — region is auto-detected from the URL. Accepted s3_url formats: s3://bucket-name, https://bucket.s3.amazonaws.com, https://bucket.s3.REGION.amazonaws.com.

List all objects in the connected S3 bucket. Returns each object's file name, size, last modified date, and a presigned URL. Optionally filter by prefix (folder path) or limit the number of results.

Upload a file to the connected S3 bucket. Two sources supported:

1. Local file: provide local_file_path (absolute path on the server).

2. Internet URL: provide source_url — file is downloaded then uploaded to S3. Optionally set object_key (S3 path/filename). Defaults to the source filename.

Read and display the contents of an object in the connected S3 bucket. Supported formats:

• Text: .txt, .csv, .json, .jsonl, .xml, .html, .md, .log, .yaml, .yml

• Excel: .xlsx, .xls — returns all sheet data as tables

• Parquet: .parquet — returns schema + first 50 rows

• PDF: .pdf — extracts text from first 10 pages

• Images: .png, .jpg, .jpeg, .gif, .webp — returns image content

• Unknown/binary: returns file metadata only.