beget-s3-mcp-ai-cli
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| BEGET_S3_POOL | No | Signing pool | ru1 |
| BEGET_S3_ALLOW | No | Independent write,delete,admin levels; read only by default | |
| BEGET_S3_ENDPOINT | No | Optional endpoint override | |
| BEGET_S3_FILE_ROOT | No | Optional confined local file root | |
| BEGET_S3_AUDIT_FILE | No | Optional private append-only audit output | |
| BEGET_S3_ACCESS_KEY_ID | No | S3 access key ID | |
| BEGET_S3_ALLOW_INSECURE | No | Set 1 only for explicit HTTP test endpoints | |
| BEGET_S3_ALLOWED_BUCKETS | No | Comma-separated bucket scope | |
| BEGET_S3_ALLOWED_PREFIXES | No | Comma-separated bucket/prefix/ scope | |
| BEGET_S3_SECRET_ACCESS_KEY | No | S3 secret access key | |
| BEGET_S3_DESTRUCTIVE_POLICY | No | BEGET_S3_DESTRUCTIVE_POLICY | confirm |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| logging | {} |
| resources | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| s3_get_objectA | Read at most 262144 bytes inline as text/base64; use presign for larger objects. |
| s3_head_objectC | Read object metadata. |
| s3_largest_objectsC | Bounded largest objects scan, default max_scan 10000; partial results carry continuation token. |
| s3_list_bucketsB | List visible buckets with pagination. |
| s3_list_multipart_uploadsC | List unfinished uploads; pass both returned markers. |
| s3_list_objectsC | List a scoped prefix, at most 1000 objects per page. |
| s3_list_partsD | List multipart parts. |
| s3_prefix_usageC | Bounded usage by first-level prefixes; paginate aggregate rows with next_result_offset. |
| s3_preview_objectC | Preview first at most 65536 bytes, detected type and CSV header. |
| s3_unfinished_uploadsC | Find uploads older than N hours (default 24), bounded by max_scan. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| capabilities | |
| config | |
| pools |
TDQS
Scored across 10 tools
Most tools target distinct resources/actions (get, head, list, prefix usage, largest objects). However s3_list_multipart_uploads and s3_unfinished_uploads overlap heavily—both surface incomplete uploads—and s3_get_object vs s3_preview_object have some boundary fuzziness, though the descriptions help differentiate.
Every tool uses a uniform s3_ prefix with consistent snake_case verb_noun structure (s3_get_object, s3_list_buckets, s3_prefix_usage). The pattern is entirely predictable.
Ten tools is well-scoped for an S3 inspection/analytics surface, with each tool earning a place. A couple of the analytics tools (largest_objects, prefix_usage) could arguably be merged, but nothing feels bloated.
The surface is read-only and covers listing, metadata, content retrieval, and analytics well, but lacks any write/lifecycle operations (put, delete, copy, presign). Notably s3_get_object instructs users to 'use presign for larger objects' yet no presign tool exists—a dead end for large-object retrieval.