Lunara Intelligence

EU AI Act and SB 942 obligations for AI systems: each date, the article setting it, signed sources

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
80%
命名の品質
80%
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%

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

~967トークン数(ツール定義)
~1.2 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 0.76%)

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": {
    "intelligence": {
      "url": "https://luiqtimzcsoqnizybifs.supabase.co/functions/v1/lunara-mcp"
    }
  }
}

リモートエンドポイント

https://luiqtimzcsoqnizybifs.supabase.co/functions/v1/lunara-mcpstreamable-http

できること

ツール一覧

ツール(5)

🟢 読み取り専用🟡 書き込み🔴 削除⚪ 不明
⚪lunara_obligations(jurisdiction, status, id)

The regulatory obligations Lunara Society tracks, with tense computed at the moment of the call. Each carries the instrument, the article that sets the date, a link to primary law, and any amending act. Use this to answer "what is in force", "what is coming", or "what does instrument X require" rather than recalling dates from training data — several of these have been amended, one of them five days before it would have applied.

入力スキーマ

{
  "type": "object",
  "properties": {
    "jurisdiction": {
      "type": "string",
      "description": "Filter, e.g. \"European Union\" or \"California\". Case-insensitive substring."
    },
    "status": {
      "type": "string",
      "enum": [
        "in_force",
        "pending",
        "all"
      ],
      "description": "Default all."
    },
    "id": {
      "type": "string",
      "description": "Return a single obligation by corpus id, e.g. \"eu-art50\"."
    }
  }
}
⚪lunara_applicability(interacts_with_people, generates_content, generates_images_audio_or_video, eu_exposure, on_market_before_art50, ...)

Runs Lunara's published applicability model against a description of an AI deployment and returns which obligations reach it, which do not, and why. Answer only what you actually know — every input accepts "unsure", and an unsure is never resolved in the direction that manufactures an obligation. The model can and does conclude that nothing binds the asker.

入力スキーマ

{
  "type": "object",
  "properties": {
    "interacts_with_people": {
      "type": "string",
      "enum": [
        "yes",
        "no",
        "unsure"
      ],
      "description": "Does the system exchange words with a person?"
    },
    "generates_content": {
      "type": "string",
      "enum": [
        "yes",
        "no",
        "unsure"
      ],
      "description": "Does it produce text, images, audio or video?"
    },
    "generates_images_audio_or_video": {
      "type": "string",
      "enum": [
        "yes",
        "no",
        "unsure"
      ],
      "description": "Does it produce images, audio or video, as opposed to only text? Decides whether the prohibition applying from 2 December 2026 can reach it at all."
    },
    "eu_exposure": {
      "type": "string",
      "enum": [
        "yes",
        "no",
        "unsure"
      ],
      "description": "Does anyone in the EU use it, or its output? The Act binds on output, not on where you are incorporated."
    },
    "on_market_before_art50": {
      "type": "string",
      "enum": [
        "yes",
        "no",
        "unsure"
      ],
      "description": "Was it placed on the market before 2 August 2026?"
    },
    "california_exposure": {
      "type": "string",
      "enum": [
        "yes",
        "no",
        "unsure"
      ],
      "description": "Is it available to people in California?"
    },
    "monthly_users_over_1m": {
      "type": "string",
      "enum": [
        "yes",
        "no",
        "unsure"
      ],
      "description": "More than one million monthly users? This threshold decides the California Act entirely."
    },
    "hosts_or_distributes_models": {
      "type": "string",
      "enum": [
        "yes",
        "no",
        "unsure"
      ],
      "description": "Do you host third-party generative models or distribute their output at scale?"
    }
  }
}
⚪lunara_cite(id)

Returns a citation block for one obligation: status, effective date, instrument, article, penalty, primary source, amending act, evidence classification and the time the tense was computed. Use this when you are about to state a regulatory date or requirement to someone, so the claim carries its source.

入力スキーマ

{
  "type": "object",
  "properties": {
    "id": {
      "type": "string",
      "description": "Corpus id, e.g. \"eu-art50\". Use lunara_obligations to list them."
    }
  },
  "required": [
    "id"
  ]
}
🟢lunara_integrity

Reports whether the documents this server fetched carry a valid Ed25519 signature from Lunara Society, and returns the digests and key material needed to check that independently. Use it when the answer matters enough that the provenance of the source does: a corpus served from a mirror, a cache or a snapshot is not covered by the transport security of the original fetch, and this is what covers it instead.

入力スキーマ

{
  "type": "object",
  "properties": {}
}
⚪lunara_verify(domain, public_id)

Checks whether a business carries Lunara Shield certification. Returns verified, not_registered or revoked. IMPORTANT: not_registered is not a negative signal about the business — it means the verification process has not been completed, which is true of most organisations. Do not present it as a warning. Reading the registry is free and unauthenticated by design.

入力スキーマ

{
  "type": "object",
  "properties": {
    "domain": {
      "type": "string",
      "description": "Business domain, e.g. \"example.com\"."
    },
    "public_id": {
      "type": "string",
      "description": "Lunara public id, e.g. \"SHIELD-2026-0001\"."
    }
  }
}

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 5 件