Content Provenance

Anchor a content-creation event to the Knox chain; returns a C2PA-aligned, FRE 902-shaped bundle.

我該用這個嗎

品質與安全性

A
說明品質
100%
結構描述完整度
100%
命名品質
90%
汙染風險
100%
權限相符程度
100%
協定合規性
100%

根據工具定義與協定合規性的自動化分析。

上下文成本

~818Token(工具定義)
~3.9 KB典型回應大小
中等的注意力影響(128k 上下文的 0.64%)

這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高,可用於其他工作的注意力就越少。

安裝

一鍵安裝

將以下內容加入你的 `claude_desktop_config.json` 檔案:

{
  "mcpServers": {
    "content-provenance": {
      "url": "https://bonissystems.com/api/knox/agents/content-provenance/mcp"
    }
  }
}

遠端端點

https://bonissystems.com/api/knox/agents/content-provenance/mcpstreamable-http

它能做什麼

工具清單

工具(2)

🟢 唯讀🟡 寫入🔴 刪除⚪ 未知
🟡anchor_creation(name, contentHash, contentType, sizeBytes, source, ...)

Anchor any creation event to the Knox event chain and return a provenance bundle. Three creation modes are supported: human_original (camera capture, original writing, recording), ai_generated (model + prompt + parameters anchored), and ai_assisted_hybrid (human-AI collaboration with edit chain). Returns the Knox anchor record, a C2PA-aligned envelope, and an FRE 902(13)/(14)-shape affidavit. Bonis Systems anchors what creators present; it does not adjudicate authorship, does not grant copyright, and does not enforce any IP claim. Requires a Knox Bearer API key on the Authorization header — unauthenticated calls are rejected.

輸入結構描述

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string",
      "description": "Display name for the work (max 256 chars)."
    },
    "contentHash": {
      "type": "string",
      "description": "SHA-256 digest of the content as 64 lowercase hex chars. The content itself is not transmitted.",
      "pattern": "^[a-fA-F0-9]{64}$"
    },
    "contentType": {
      "type": "string",
      "description": "MIME type (max 128 chars)."
    },
    "sizeBytes": {
      "type": "integer",
      "minimum": 0,
      "description": "Content size in bytes."
    },
    "source": {
      "type": "string",
      "enum": [
        "human_original",
        "ai_generated",
        "ai_assisted_hybrid"
      ],
      "description": "Creation source."
    },
    "ai": {
      "type": "object",
      "description": "AI-generation metadata (required when source = ai_generated).",
      "properties": {
        "model": {
          "type": "string",
          "description": "Model identifier (e.g., openai/sora-2, google/veo-3)."
        },
        "provider": {
          "type": "string",
          "description": "Provider name."
        },
        "prompt": {
          "type": "string",
          "description": "Plain-text prompt (will be hashed in the anchor)."
        },
        "promptHash": {
          "type": "string",
          "description": "Pre-hashed prompt (preferred for privacy)."
        },
        "parameters": {
          "type": "object",
          "description": "Model parameters (hashed in the anchor)."
        },
        "providerReceiptId": {
          "type": "string",
          "description": "Provider's job/run ID."
        },
        "generatedAt": {
          "type": "string",
          "description": "ISO timestamp from the provider."
        }
      }
    },
    "hybrid": {
      "type": "object",
      "description": "Hybrid-creation metadata (required when source = ai_assisted_hybrid).",
      "properties": {
        "humanContribution": {
          "type": "string",
          "description": "Description of the human creative role."
        },
        "aiContribution": {
          "type": "string",
          "description": "Description of the AI's role."
        },
        "ai": {
          "type": "object",
          "description": "Optional AI metadata (same shape as 'ai')."
        },
        "editChain": {
          "type": "array",
          "description": "Optional edit-history entries; hashed.",
          "items": {
            "type": "object",
            "properties": {
              "description": {
                "type": "string"
              },
              "at": {
                "type": "string"
              }
            },
            "required": [
              "description",
              "at"
            ]
          }
        }
      },
      "required": [
        "humanContribution",
        "aiContribution"
      ]
    },
    "human": {
      "type": "object",
      "description": "Human-original metadata (optional when source = human_original).",
      "properties": {
        "captureMethod": {
          "type": "string",
          "description": "Camera / device / instrument used."
        },
        "captureAt": {
          "type": "string",
          "description": "ISO timestamp of capture."
        },
        "captureLocation": {
          "type": "string",
          "description": "Location string; hashed before anchoring."
        },
        "authorClaim": {
          "type": "string",
          "description": "Author identity claim (name, DID, etc.)."
        }
      }
    }
  },
  "required": [
    "name",
    "contentHash",
    "source"
  ],
  "additionalProperties": false
}
🟢verify_provenance(hash)

Verify an anchored content-provenance record. Given a SHA-256 anchor hash (the payload_hash from a prior anchor_creation call), return the anchor record, predecessor hash, sequence number, and timestamp. Public — no authentication required. The verification path itself is also accessible at GET /api/knox/verify?hash=<hash>.

輸入結構描述

{
  "type": "object",
  "properties": {
    "hash": {
      "type": "string",
      "description": "SHA-256 anchor hash (64 lowercase hex chars).",
      "pattern": "^[a-fA-F0-9]{64}$"
    }
  },
  "required": [
    "hash"
  ],
  "additionalProperties": false
}

社群

為此伺服器評分

證據

近期觀測

已驗證未記錄版本2 個工具
已驗證未記錄版本2 個工具
已驗證未記錄版本2 個工具