closetscan
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CLOSETSCAN_CATALOGUE | No | Path to the catalogue directory. If not provided, the server uses the positional argument or defaults to './out'. |
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
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_garmentsA | List garments in the wardrobe, optionally filtered. Returns compact records; use get_garment for full detail. Paginated via limit/offset. |
| get_garmentA | Full record for one garment: all attributes, every view with its provenance, and file paths. |
| search_garmentsB | Free-text search over names, descriptions and attributes. Returns compact records, best match first. |
| search_narrationA | Search what the wearer said about their clothes while filming — materials, where things came from, and how they feel about them. Use this for questions about history, feelings or origin; use search_garments for questions about appearance. |
| log_wearA | Record that a garment was worn. Appends to the wear log; never modifies the catalogue. Date defaults to today. |
| get_wear_historyA | Read the wear log: individual entries plus per-garment totals, first/last worn, never-worn items, and cost-per-wear where a cost attribute exists. |
| list_attributesA | Which attributes this catalogue actually carries and what values they take. Call this before guessing filter values. |
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 7 tools
Each tool has a clearly distinct purpose: listing, fetching, searching garments, searching narration, logging wear, reading wear history, and listing attributes. The only similar pair, search_garments and search_narration, is explicitly differentiated by content domain and intended use.
All tool names follow a consistent snake_case verb_noun pattern: list_garments, get_garment, search_garments, search_narration, log_wear, get_wear_history, list_attributes. There are no mixed conventions or vague verbs.
Seven tools is a well-scoped set for a wardrobe scanning and wear-tracking server. Each tool covers a distinct operation without redundancy or bloat.
The surface covers the full apparent workflow: discover available attributes, list/filter/search garments, get full details, search narration, log a wear event, and read aggregated wear history. Catalogue mutation is explicitly out of scope, so its absence is not a gap.