Skip to main content
Glama
stufently

yandex-s3-mcp-ai-cli

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
YANDEX_S3_POOLNoSigning poolru-central1
YANDEX_S3_ALLOWNoIndependent write,delete,admin levels; read only by default
YANDEX_S3_ENDPOINTNoOptional endpoint override
YANDEX_S3_FILE_ROOTNoOptional confined local file root
YANDEX_S3_AUDIT_FILENoOptional private append-only audit output
YANDEX_S3_ACCESS_KEY_IDNoS3 access key ID
YANDEX_S3_ALLOW_INSECURENoSet 1 only for explicit HTTP test endpoints
YANDEX_S3_ALLOWED_BUCKETSNoComma-separated bucket scope
YANDEX_S3_ALLOWED_PREFIXESNoComma-separated bucket/prefix/ scope
YANDEX_S3_SECRET_ACCESS_KEYNoS3 secret access key
YANDEX_S3_DESTRUCTIVE_POLICYNoYANDEX_S3_DESTRUCTIVE_POLICYconfirm

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

CapabilityDetails
tools
{
  "listChanged": true
}
logging
{}
resources
{
  "listChanged": true
}

Tools

Functions exposed to the LLM to take actions

NameDescription
s3_get_bucket_configB

Read location, versioning, CORS, policy and Object Lock; report absent/unsupported configuration.

s3_get_objectA

Read at most 262144 bytes inline as text/base64; use presign for larger objects.

s3_get_object_taggingC

Get object tags.

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_object_versionsC

List versions and delete markers with both pagination 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_presign_getC

Create signed GET URL; default 3600 seconds, provider maximum is unverified.

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

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription
capabilities
config
pools

TDQS

C2.8/5.0

Scored across 14 tools

Disambiguation4/5

Most tools target a distinct resource+read operation (buckets, objects, versions, tags, parts, usage). The main ambiguity is s3_list_multipart_uploads vs s3_unfinished_uploads, which both surface unfinished multipart uploads (one filtered by age); get/head/preview also overlap slightly on reading object data, but descriptions differentiate the intent.

Naming Consistency4/5

Everything shares the s3_ prefix and snake_case, which is predictable. Minor deviations exist: largest_objects, prefix_usage, and unfinished_uploads drop the leading verb, and presign_get inverts the verb/noun order, so the verb_noun pattern isn't perfectly uniform.

Tool Count5/5

14 tools sit squarely in the well-scoped 3-15 range and each maps to a plausible inspection task (list, get, head, tags, versions, multipart, presign, usage, preview). No filler or redundant tools beyond the minor upload overlap.

Completeness4/5

The surface reads as a read-only S3 inspection/analysis domain and covers buckets, objects, versions, tags, multipart uploads, presigning, and usage aggregation well. Gaps are minor for that scope (no object ACL read, no abort of unfinished uploads, and full-object download only via presign), which agents can work around.

Maintenance

ActivityMaintained
ResponsivenessNo issues