ruthven

Read-only artwork provenance: Origin Passports, evidence states, Merkle proofs checkable on Ethereum

使うべきか

品質と安全性

A
説明の品質
98%
スキーマの完全性
86%
命名の品質
80%
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(3)

  • HIGHTool poisoning patterns detected
  • MEDIUMTool 'ruthven_describe' description contains placeholder textruthven_describe 内
  • INFOTool description contains placeholder or incomplete textruthven_describe 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

~1,513トークン数(ツール定義)
~971 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 1.18%)

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": {
    "ruthven": {
      "url": "https://ruthven.ai/api/ruthven/mcp"
    }
  }
}

リモートエンドポイント

https://ruthven.ai/api/ruthven/mcpstreamable-http

できること

ツール一覧

ツール(8)

🟢 読み取り専用🟡 書き込み🔴 削除⚪ 不明
🟢ruthven_get_asset(asset_id, include_evidence)

The universal RUTHVEN asset record: identity, tokenization, provenance, source works, components, construction sequence, hashes, documents, rights, verified / contextual / inferred facts, unknowns, and counts. Claims carry evidence ids; pass include_evidence=true for the full evidence records as well (large).

入力スキーマ

{
  "type": "object",
  "properties": {
    "asset_id": {
      "type": "string",
      "description": "The asset: \"PT-0001\", a RUTHVEN ID such as \"RUTHVEN-PT-0000001\", or a work number such as \"1\"."
    },
    "include_evidence": {
      "type": "boolean",
      "description": "Include every evidence record and the evidence graph. Default false."
    }
  },
  "required": [
    "asset_id"
  ],
  "additionalProperties": false
}
🟢ruthven_list_evidence(asset_id, status, type, kind, q, ...)

The evidence records behind an asset, each with a stable evidence_id, its source (document, locator, ipfs uri, gateway url, ledger claim id), a SHA-256, a verification state and freshness timestamps. Filter by status (VERIFIED, CONTEXT, INFERRED), type, kind, or a text query.

入力スキーマ

{
  "type": "object",
  "properties": {
    "asset_id": {
      "type": "string",
      "description": "The asset: \"PT-0001\", a RUTHVEN ID such as \"RUTHVEN-PT-0000001\", or a work number such as \"1\"."
    },
    "status": {
      "type": "string",
      "enum": [
        "VERIFIED",
        "CONTEXT",
        "INFERRED"
      ]
    },
    "type": {
      "type": "string"
    },
    "kind": {
      "type": "string"
    },
    "q": {
      "type": "string",
      "description": "Text to look for in the label or statement."
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 500
    },
    "offset": {
      "type": "integer",
      "minimum": 0
    }
  },
  "required": [
    "asset_id"
  ],
  "additionalProperties": false
}
🟢ruthven_get_evidence(asset_id, evidence_id)

Retrieve the source record behind a stable evidence id (EVID-…) or an unknown id (UNK-…): where it was read from, its hash, its state, and how fresh it is.

入力スキーマ

{
  "type": "object",
  "properties": {
    "asset_id": {
      "type": "string",
      "description": "The asset: \"PT-0001\", a RUTHVEN ID such as \"RUTHVEN-PT-0000001\", or a work number such as \"1\"."
    },
    "evidence_id": {
      "type": "string"
    }
  },
  "required": [
    "asset_id",
    "evidence_id"
  ],
  "additionalProperties": false
}
🟢ruthven_get_provenance(asset_id)

Provenance and lineage: the timeline, source works, generated elements, components, the construction sequence, relationships, chain identity, tokenization, and the evidence graph (cut_from, placed_as, pinned_as, pictured_by, hash_of).

入力スキーマ

{
  "type": "object",
  "properties": {
    "asset_id": {
      "type": "string",
      "description": "The asset: \"PT-0001\", a RUTHVEN ID such as \"RUTHVEN-PT-0000001\", or a work number such as \"1\"."
    }
  },
  "required": [
    "asset_id"
  ],
  "additionalProperties": false
}
🟢ruthven_verify_claim(asset_id, evidence_ids)

Given the evidence ids a claim rests on, return the state the claim earns (the weakest among them), each record's hash and location, and how to check it independently of RUTHVEN. Deterministic; no model is involved.

入力スキーマ

{
  "type": "object",
  "properties": {
    "asset_id": {
      "type": "string",
      "description": "The asset: \"PT-0001\", a RUTHVEN ID such as \"RUTHVEN-PT-0000001\", or a work number such as \"1\"."
    },
    "evidence_ids": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "minItems": 1,
      "maxItems": 50
    }
  },
  "required": [
    "asset_id",
    "evidence_ids"
  ],
  "additionalProperties": false
}
🟢ruthven_get_proof(asset_id, evidence_ids, paths)

A Merkle proof that evidence records are part of the issued Origin Passport, with the entry each rests on and the steps to check it without trusting RUTHVEN: SHA-256 over the entry, keccak256 up the proof, and the root compared with the one in the published Passport. It proves that the record contains the entry; it does not make a statement true. With neither evidence_ids nor paths, returns the paths that can be proved. Deterministic; no model is involved.

入力スキーマ

{
  "type": "object",
  "properties": {
    "asset_id": {
      "type": "string",
      "description": "The asset: \"PT-0001\", a RUTHVEN ID such as \"RUTHVEN-PT-0000001\", or a work number such as \"1\"."
    },
    "evidence_ids": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "maxItems": 50,
      "description": "Stable evidence ids (EVID-…)."
    },
    "paths": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "maxItems": 50,
      "description": "Entry paths in the Passport, e.g. \"identity.name\" or \"module.collection.copyrightOwner\"."
    }
  },
  "required": [
    "asset_id"
  ],
  "additionalProperties": false
}
🟢ruthven_ask(asset_id, question)

Ask a question about one asset. Returns structured JSON only: an answer, claims (each with a verification state and the evidence ids it rests on), unknowns, the full cited evidence records, and follow-up questions. Never a valuation; never a recommendation to act.

入力スキーマ

{
  "type": "object",
  "properties": {
    "asset_id": {
      "type": "string",
      "description": "The asset: \"PT-0001\", a RUTHVEN ID such as \"RUTHVEN-PT-0000001\", or a work number such as \"1\"."
    },
    "question": {
      "type": "string",
      "maxLength": 500
    }
  },
  "required": [
    "asset_id",
    "question"
  ],
  "additionalProperties": false
}
🟢ruthven_describe

What RUTHVEN is and what an agent may do with it: the verification states, the permission model (READ and ANALYSE only), the asset types (live and placeholder), and the JSON API endpoints.

入力スキーマ

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}

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 8 件