s3-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_bucketsA | List all buckets accessible with the configured credentials. |
| list_objectsA | List objects in a bucket (single page, up to max_keys). Returns objects with key/size/last_modified plus a truncated flag when more results exist. |
| get_objectA | Read an object. UTF-8 content returns as text; anything else as base64. |
| stat_objectA | Get object metadata (size, etag, content type, last modified). |
| presign_getB | Generate a pre-signed GET URL valid for expires_s seconds (max 604800). |
| presign_putC | Generate a pre-signed PUT URL valid for expires_s seconds (max 604800). |
| put_objectC | Write an object. Set base64=true when body is base64-encoded binary. |
| delete_objectC | Delete an object from a bucket. |
| copy_objectC | Copy an object within or across buckets on the same endpoint. |
| create_bucketC | Create a bucket in the configured region. |
| delete_bucketA | Delete a bucket (must be empty). |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 11 tools
Every tool maps to a distinct S3 operation: bucket listing/creation/deletion, object listing/read/metadata/write/delete/copy, and presigned URL generation for GET vs PUT. There is no functional overlap that would cause an agent to select the wrong tool.
All tool names follow the same snake_case verb_noun pattern (list_buckets, get_object, presign_put, create_bucket, etc.). The naming is predictable and consistent across the entire surface.
With 11 tools, the set is well-scoped for an S3-focused server. Each tool covers a core operation without extraneous additions or redundant convenience wrappers.
The server covers bucket lifecycle and object CRUD, including copying and presigned URLs, so common workflows are fully supported. Minor gaps exist around pagination for large object listings and advanced operations like multipart uploads, but these are not severe for typical usage.