cc0-library
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": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_assetsA | Find CC0 1.0 (public-domain dedication) images, audio, video, HDRIs, textures, 3D models and museum artworks by keyword, returning only items whose CC0 status was checked. Use it first to discover candidates; then call get_asset for download files and a fresh license re-check. Use list_sources instead to answer which sites are CC0. Do not use it for CC BY, CC BY-SA or other 'free' licenses: they are filtered out. Behavior: read-only, no API key, live HTTPS calls to each source (usually 2-10 s). A failing source is listed in |
| get_assetA | Fetch one asset's details and download files by an id from search_assets, re-checking at the source that it is still CC0. Use it after search_assets when the user wants to download or inspect an item; it cannot search, so call search_assets first if you have no id. Returns an error (do not retry the same id) when the id is malformed, the item was removed, or the source no longer reports CC0. Behavior: read-only, no API key, one or two live HTTPS calls. Poly Haven lists up to 60 resolution/format variants; ambientCG returns zip packs; Sketchfab returns only the model page because its downloads need the user's own login. |
| list_sourcesA | List the curated catalog of CC0 asset sites, each with its license page, scope and dated evidence, plus popular 'free' sites that are NOT CC0 (e.g. Unsplash, Pixabay) and candidates still pending verification. Use it to answer 'is site X CC0?' or to suggest sites to browse by hand; use search_assets instead to find actual assets. Behavior: reads a bundled JSON file, so no network access, instant and deterministic. |
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 3 tools
Each tool targets a distinct action on a distinct object: search_assets discovers, get_asset fetches one item by id, list_sources answers catalog/licensing questions. The descriptions explicitly cross-reference each other ('use list_sources instead to answer which sites are CC0', 'cannot search, call search_assets first'), leaving no plausible misselection.
All three names follow a clean verb_noun snake_case pattern (search_assets, get_asset, list_sources) with consistent pluralization for collections vs singular for single-item retrieval.
Three tools is on the lean side, but for a read-only CC0 discovery service the discover -> inspect/download -> check-source triad is exactly the needed surface with no filler. It sits just under the ideal band rather than being genuinely thin.
Search, item detail with download variants, and license/source provenance cover the core read-only lifecycle, with no create/update/delete needed for a public-domain index. Minor gaps exist (no pagination or browse-by-source/collection tool), but agents can work around them via keyword queries and the source catalog.