mcp

AI disclosure laws by business and state, each law in full, and a website AI-notice check.

使うべきか

品質と安全性

A
説明の品質
100%
スキーマの完全性
93%
命名の品質
95%
ポイズニングのリスク
80%
権限の一致
100%
プロトコルへの準拠
100%

検出事項(2)

  • HIGHTool poisoning patterns detected
  • MEDIUMTool description contains URL to non-standard domainget_law 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

~1,474トークン数(ツール定義)
~3.6 KB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 1.15%)

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": {
    "mcp": {
      "url": "https://botnotice.app/mcp"
    }
  }
}

リモートエンドポイント

https://botnotice.app/mcpstreamable-http

できること

ツール一覧

ツール(4)

🟢 読み取り専用🟡 書き込み🔴 削除⚪ 不明
🟢laws_for_business(use_cases, states, all_us, eu, uk, ...)

Given how a business uses AI and where its customers are, returns the laws in force and the ones coming, each with what must be disclosed, when, the penalties and the sources, plus the notice rules that satisfy all of them. Free, no account. Not legal advice.

入力スキーマ

{
  "type": "object",
  "properties": {
    "use_cases": {
      "description": "How the business uses AI. Codes: support_chatbot (Customer-service / FAQ chatbot); sales_chatbot (Sales, lead-capture, or booking chatbot); companion_chatbot (Chatbot with memory, persona, or relationship features); voice_agent (AI phone / voice agent); ai_content (AI-generated marketing text, images, or video); synthetic_performers (AI-generated 'people' in ads); ai_hiring (AI in hiring, screening, or HR decisions); healthcare (AI in patient diagnosis, treatment, or care); mental_health (AI offering emotional support or therapy-like help); advice (AI giving financial, legal, or medical guidance); automated_decisions (AI deciding eligibility (credit, housing, insurance, benefits)). Default: support_chatbot.",
      "type": "array",
      "items": {
        "type": "string",
        "enum": [
          "support_chatbot",
          "sales_chatbot",
          "companion_chatbot",
          "voice_agent",
          "ai_content",
          "synthetic_performers",
          "ai_hiring",
          "healthcare",
          "mental_health",
          "advice",
          "automated_decisions"
        ]
      }
    },
    "states": {
      "description": "Two-letter U.S. state codes where the customers are, e.g. [\"CA\",\"NY\"]. Leave out with all_us.",
      "type": "array",
      "items": {
        "type": "string",
        "minLength": 2,
        "maxLength": 2
      }
    },
    "all_us": {
      "description": "Customers anywhere in the U.S. The default when no place is given.",
      "type": "boolean"
    },
    "eu": {
      "description": "People in the European Union can use the AI.",
      "type": "boolean"
    },
    "uk": {
      "description": "People in the United Kingdom can use the AI.",
      "type": "boolean"
    },
    "minors": {
      "description": "Whether minors may use it: no, possible (default), or directed (aimed at them).",
      "type": "string",
      "enum": [
        "no",
        "possible",
        "directed"
      ]
    },
    "memory": {
      "description": "The bot remembers people or builds rapport (companion-style).",
      "type": "boolean"
    },
    "licensed_profession": {
      "description": "A state-licensed profession: health, legal, accounting.",
      "type": "boolean"
    },
    "big_platform": {
      "description": "10 million or more unique monthly U.S. visitors.",
      "type": "boolean"
    }
  },
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}
🟢get_law(slug)

The full record for one law: who must comply, what to disclose, timing, duties, exemptions, penalties, enforcement, sources and the last-verified date. Slugs come from list_laws or the dataset at https://botnotice.app/datasets/ai-disclosure-laws.json.

入力スキーマ

{
  "type": "object",
  "properties": {
    "slug": {
      "type": "string",
      "description": "The law's slug, e.g. california-sb-243 or eu-ai-act-article-50."
    }
  },
  "required": [
    "slug"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}
🟢list_laws(jurisdiction, status, applies_to)

Every AI disclosure law BotNotice tracks (U.S. states, federal, EU, UK), with status and effective date, optionally filtered. Also the pending bills.

入力スキーマ

{
  "type": "object",
  "properties": {
    "jurisdiction": {
      "description": "A code (CA, NY, US-FED, EU, UK) or a name.",
      "type": "string"
    },
    "status": {
      "type": "string",
      "enum": [
        "in_force",
        "enacted_future",
        "pending",
        "enjoined"
      ]
    },
    "applies_to": {
      "description": "Only laws triggered by this kind of AI use.",
      "type": "string",
      "enum": [
        "support_chatbot",
        "sales_chatbot",
        "companion_chatbot",
        "voice_agent",
        "ai_content",
        "synthetic_performers",
        "ai_hiring",
        "healthcare",
        "mental_health",
        "advice",
        "automated_decisions"
      ]
    }
  },
  "$schema": "https://json-schema.org/draft/2020-12/schema"
}
🟢check_website(use_cases, states, all_us, eu, uk, ...)

Reads a public website: which chat or voice-AI tools it runs, whether an AI disclosure is already shown, and, for the business described, which laws that leaves unmet. The same check as the free scan at botnotice.app/scan, without the browser pass. Not legal advice.

入力スキーマ

{
  "type": "object",
  "properties": {
    "use_cases": {
      "description": "How the business uses AI. Codes: support_chatbot (Customer-service / FAQ chatbot); sales_chatbot (Sales, lead-capture, or booking chatbot); companion_chatbot (Chatbot with memory, persona, or relationship features); voice_agent (AI phone / voice agent); ai_content (AI-generated marketing text, images, or video); synthetic_performers (AI-generated 'people' in ads); ai_hiring (AI in hiring, screening, or HR decisions); healthcare (AI in patient diagnosis, treatment, or care); mental_health (AI offering emotional support or therapy-like help); advice (AI giving financial, legal, or medical guidance); automated_decisions (AI deciding eligibility (credit, housing, insurance, benefits)). Default: support_chatbot.",
      "type": "array",
      "items": {
        "type": "string",
        "enum": [
          "support_chatbot",
          "sales_chatbot",
          "companion_chatbot",
          "voice_agent",
          "ai_content",
          "synthetic_performers",
          "ai_hiring",
          "healthcare",
          "mental_health",
          "advice",
          "automated_decisions"
        ]
      }
    },
    "states": {
      "description": "Two-letter U.S. state codes where the customers are, e.g. [\"CA\",\"NY\"]. Leave out with all_us.",
      "type": "array",
      "items": {
        "type": "string",
        "minLength": 2,
        "maxLength": 2
      }
    },
    "all_us": {
      "description": "Customers anywhere in the U.S. The default when no place is given.",
      "type": "boolean"
    },
    "eu": {
      "description": "People in the European Union can use the AI.",
      "type": "boolean"
    },
    "uk": {
      "description": "People in the United Kingdom can use the AI.",
      "type": "boolean"
    },
    "minors": {
      "description": "Whether minors may use it: no, possible (default), or directed (aimed at them).",
      "type": "string",
      "enum": [
        "no",
        "possible",
        "directed"
      ]
    },
    "memory": {
      "description": "The bot remembers people or builds rapport (companion-style).",
      "type": "boolean"
    },
    "licensed_profession": {
      "description": "A state-licensed profession: health, legal, accounting.",
      "type": "boolean"
    },
    "big_platform": {
      "description": "10 million or more unique monthly U.S. visitors.",
      "type": "boolean"
    },
    "url": {
      "type": "string",
      "format": "uri",
      "description": "The website's address, e.g. https://example.com."
    }
  },
  "required": [
    "url"
  ],
  "$schema": "https://json-schema.org/draft/2020-12/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 4 件