加载中…
Check classifier confidence against accuracy, fit temperature scaling and save local reports.
Calibration Explorer 是 ChatHome Skills 收录的 MCP 条目，来源为 Official MCP Registry，质量分 78/100。 作为 Model Context Protocol 服务器，它向 Claude、Cursor、Copilot 等兼容 MCP 的 LLM 客户端暴露可直接调用的工具，让 agent 的能力超出模型内置范围。 该条目由 ChatHome Skills 的每日抓取从官方 registry 和 GitHub 发现查询中收录，每次运行都会重新核验仓库事实、新鲜度信号和安装元数据。 质量分综合了官方 registry 收录情况、可用安装命令、许可证完整性、仓库活跃度和 GitHub star 趋势，完整算法说明见来源页。安装命令已列于上方，可直接复制使用。 在将 Calibration Explorer 加入生产 agent 工作流前，请核对上方的最近更新日期和仓库状态——下方事实快照是最近一次抓取的时点值。
npx -y @m-sanchez/calibration-explorer-mcp@0.2.0运行此命令前，请先核对上游源码。
{
"_meta": {
"io.modelcontextprotocol.registry/official": {
"status": "active",
"isLatest": true,
"updatedAt": "2026-10-05T12:17:38.931579Z",
"publishedAt": "2026-10-05T12:17:38.931579Z",
"statusChangedAt": "2026-10-05T12:17:38.931579Z"
}
},
"server": {
"name": "io.github.m-sanchez/calibration-explorer",
"title": "Calibration Explorer",
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
"version": "0.2.0",
"packages": [
{
"version": "0.2.0",
"transport": {
"type": "stdio"
},
"identifier": "@m-sanchez/calibration-explorer-mcp",
"runtimeHint": "npx",
"registryType": "npm",
"registryBaseUrl": "https://registry.npmjs.org",
"packageArguments": [
{
"name": "--input-root",
"type": "named",
"format": "filepath",
"isRepeated": true,
"isRequired": true,
"description": "Existing absolute directory whose prediction CSV or JSON files the server may read. Paths outside it are refused. Repeat for more directories."
},
{
"name": "--output-root",
"type": "named",
"format": "filepath",
"isRepeated": true,
"isRequired": true,
"description": "Existing absolute directory where the server may create new report folders. It never overwrites files. Repeat for more directories."
}
]
}
],
"repository": {
"id": "1402908024",
"url": "https://github.com/m-sanchez/calibration-explorer",
"source": "github",
"subfolder": "packages/mcp"
},
"websiteUrl": "https://github.com/m-sanchez/calibration-explorer/blob/main/docs/mcp.md",
"description": "Check classifier confidence against accuracy, fit temperature scaling and save local reports."
}
}