MCP低风险未认领
Shelfmark
Local, privacy-first document catalogue for AI agents: metadata-only discovery, no cloud, no RAG.
Dankaro-projectsdankaro-projects/shelfmark
server.json
{
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
"name": "io.github.Dankaro-projects/shelfmark",
"description": "Local, privacy-first document catalogue for AI agents: metadata-only discovery, no cloud, no RAG.",
"title": "Shelfmark",
"repository": {
"url": "https://github.com/Dankaro-projects/shelfmark",
"source": "github"
},
"version": "0.4.9",
"packages": [
{
"registryType": "pypi",
"identifier": "shelfmark",
"version": "0.4.9",
"runtimeHint": "uvx",
"transport": {
"type": "stdio"
},
"packageArguments": [
{
"value": "serve",
"type": "positional"
}
]
}
]
}权限
声明检测
运行代码—
python安装—
pypi:shelfmark@0.4.9安装时运行脚本—无
网络无无
需要的凭据无无
工作区外的路径—无
智能体工具—无
检查
低风险 · 没有发现需要提醒的地方。
未经人工审核 · 已做规则检查;模型审核尚未开启。
版本
- #10.4.9最新2026年10月7日
Shelfmark在 Codeg 中打开