TheFaceAnalysis

Face shape rules and a 102-face open measurement dataset. Read-only, no photos.

使うべきか

品質と安全性

A
説明の品質
90%
スキーマの完全性
83%
命名の品質
97%
ポイズニングのリスク
100%
権限の一致
100%
プロトコルへの準拠
100%

検出事項(1)

  • LOWTool 'get_methodology' description lacks action verbget_methodology 内

ツール定義とプロトコルへの準拠に関する自動分析に基づいています。

コンテキストコスト

~1,098トークン数(ツール定義)
~858 B一般的なレスポンスサイズ
注意への影響は中程度(128k コンテキストの 0.86%)

これは、サーバーのツールがモデルのコンテキストに読み込まれるたびに消費されるおおよそのトークン数です。数が多いほど、ほかのタスクに使える注意が減ります。

インストール

ワンクリックインストール

これを `claude_desktop_config.json` ファイルに追加してください:

{
  "mcpServers": {
    "face-analysis": {
      "url": "https://mcp.thefaceanalysis.com/mcp"
    }
  }
}

リモートエンドポイント

https://mcp.thefaceanalysis.com/mcpstreamable-http

できること

ツール一覧

ツール(7)

🟢 読み取り専用🟡 書き込み🔴 削除⚪ 不明
🟢get_reference_statistics(measure, group)

Percentiles (p10, p25, median, p75, p90, min, max) of facial measurements from 102 adult faces (49 women, 53 men) of the Face Research Lab London Set, measured with a 478-point MediaPipe landmarker. Measures: composite score, symmetry, golden ratio fit, fWHR, midface ratio, pupillary distance, canthal tilt. Aggregates only; one research set photographed in one city, so these describe these faces, not a population.

入力スキーマ

{
  "type": "object",
  "properties": {
    "measure": {
      "type": "string",
      "enum": [
        "composite",
        "symmetry",
        "golden",
        "fwhr",
        "midface",
        "pd",
        "tilt"
      ],
      "description": "One measure. Omit for all."
    },
    "group": {
      "type": "string",
      "enum": [
        "all",
        "female",
        "male"
      ],
      "description": "all, female or male. Omit for all three."
    }
  },
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢list_face_types(category)

Lists the types the site's detectors use, with slug, name, page URL and how many of the 102 reference faces each type covered. The split shows how the detector divides these faces, not how common a type is in a population.

入力スキーマ

{
  "type": "object",
  "properties": {
    "category": {
      "type": "string",
      "enum": [
        "face",
        "eye",
        "lip",
        "nose"
      ],
      "description": "Omit for all four categories."
    }
  },
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢get_face_type(category, slug)

Definition and how the type is measured from a front photo (the exact threshold rule), plus its page URL. Example: category 'face', slug 'oval'.

入力スキーマ

{
  "type": "object",
  "properties": {
    "category": {
      "type": "string",
      "enum": [
        "face",
        "eye",
        "lip",
        "nose"
      ]
    },
    "slug": {
      "type": "string",
      "description": "e.g. oval, heart, hooded, upturned"
    }
  },
  "required": [
    "category",
    "slug"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢classify_face_shape(face_length, cheekbone_width, forehead_width, jaw_width)

Runs the same seven-rule face shape classifier as thefaceanalysis.com/face-shape-detector on four distances (any consistent unit: pixels, mm or landmark units). Returns the shape, the rule that matched and the four ratios. It does not look at photos: to measure a photo, use the widget (get_embed_snippet) or the site. Borderline faces can flip between two shapes; no accuracy figure is claimed because the reference set has no labelled face types.

入力スキーマ

{
  "type": "object",
  "properties": {
    "face_length": {
      "type": "number",
      "exclusiveMinimum": 0,
      "description": "Top of the forehead surface to the bottom of the chin"
    },
    "cheekbone_width": {
      "type": "number",
      "exclusiveMinimum": 0,
      "description": "Widest point across the cheekbones"
    },
    "forehead_width": {
      "type": "number",
      "exclusiveMinimum": 0,
      "description": "Width across the temples"
    },
    "jaw_width": {
      "type": "number",
      "exclusiveMinimum": 0,
      "description": "Width across the jaw"
    }
  },
  "required": [
    "face_length",
    "cheekbone_width",
    "forehead_width",
    "jaw_width"
  ],
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢get_methodology(include_changelog)

How the numbers are made: the landmark model, every classification threshold, how the 1-10 score is built, and how it correlated with 2,513 human raters on the same faces (it did not predict them). Includes the method change history.

入力スキーマ

{
  "type": "object",
  "properties": {
    "include_changelog": {
      "type": "boolean",
      "description": "Also return the dated change history."
    }
  },
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢get_citation

Citation text, license (CC BY 4.0 for the aggregate numbers) and the source photo set. Use when quoting a number.

入力スキーマ

{
  "type": "object",
  "properties": {},
  "$schema": "http://json-schema.org/draft-07/schema#"
}
🟢get_embed_snippet(size)

HTML a website owner can paste to add the free face shape finder (it measures the visitor's photo in their browser, no sign-up). Includes the visible credit link the terms ask for.

入力スキーマ

{
  "type": "object",
  "properties": {
    "size": {
      "type": "string",
      "enum": [
        "compact",
        "standard",
        "wide"
      ],
      "description": "compact 360px, standard 480px, wide 720px"
    }
  },
  "additionalProperties": false,
  "$schema": "http://json-schema.org/draft-07/schema#"
}

コミュニティ

このサーバーを評価する

エビデンス

最近の観測

検証済みバージョンは記録されていませんツール 7 件