Sketchlib
Search a large 3D model library and download converted GLB/FBX/USDZ assets via signed URLs.
我該用這個嗎
品質與安全性
根據工具定義與協定合規性的自動化分析。
上下文成本
這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高,可用於其他工作的注意力就越少。
安裝
一鍵安裝
將以下內容加入你的 `claude_desktop_config.json` 檔案:
{
"mcpServers": {
"sketchlib": {
"url": "https://sketchlib.com/mcp"
}
}
}遠端端點
https://sketchlib.com/mcpstreamable-http它能做什麼
工具清單
工具(3)
🟢search_models(keyword, category, tag, min_faces, max_faces, ...)
Search the Sketchlib library by keyword, optionally narrowed by category, tag, or face-count range. Returns paginated metadata and a preview image URL. has_more reports whether a further page exists; raise offset by limit to fetch it.
輸入結構描述
{
"type": "object",
"properties": {
"keyword": {
"type": "string",
"minLength": 3,
"description": "Search terms, at least 3 characters. Matched against title, slug, tags, categories and description."
},
"category": {
"description": "Filter by category.",
"type": "string"
},
"tag": {
"description": "Filter by tag.",
"type": "string"
},
"min_faces": {
"description": "Minimum face count.",
"type": "integer",
"minimum": -9007199254740991,
"maximum": 9007199254740991
},
"max_faces": {
"description": "Maximum face count.",
"type": "integer",
"minimum": -9007199254740991,
"maximum": 9007199254740991
},
"limit": {
"description": "Results per page, 1-50. Defaults to 20.",
"type": "integer",
"minimum": 1,
"maximum": 50
},
"offset": {
"description": "Pagination offset.",
"type": "integer",
"minimum": 0,
"maximum": 9007199254740991
}
},
"required": [
"keyword"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢get_model(model_id)
Return full metadata for one model, including whether it is downloadable and its preview image URL.
輸入結構描述
{
"type": "object",
"properties": {
"model_id": {
"type": "string",
"description": "The model_id from search_models."
}
},
"required": [
"model_id"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢download_model(model_id)
Return a signed download URL for a model zip, valid for 1 hour. Consumes one credit. Subscription plans are capped at 100 downloads per day; past that cap the account's credits are used, so a capped subscriber who holds credits is not blocked.
輸入結構描述
{
"type": "object",
"properties": {
"model_id": {
"type": "string",
"description": "The model_id from search_models."
}
},
"required": [
"model_id"
],
"$schema": "http://json-schema.org/draft-07/schema#"
}社群
證據