ScreenSeal

Sanctions screening for AI agents: check a name against OFAC and EU lists. Free during launch.

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
80%
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

~251Token(工具定義)
~1.4 KB典型回應大小
極小的注意力影響(128k 上下文的 0.20%)

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": {
    "screenseal-mcp": {
      "url": "https://screenseal-mcp.agent-tollbooth.workers.dev/mcp"
    }
  }
}

遠端端點

https://screenseal-mcp.agent-tollbooth.workers.dev/mcpstreamable-http

它能做什麼

工具清單

工具(1)

🟢 唯讀🟡 寫入🔴 刪除⚪ 未知
🟢screenseal_screen(name, dob, nationality)

Screen a person or organization name against the current OFAC SDN, OFAC Consolidated Non-SDN, and EU financial sanctions datasets. Returns potential fuzzy matches with confidence scores, per-list provenance (list versions, source URLs, SHA-256 digests), and a cryptographic EIP-712 attestation sealing the exact response issued. Informational screening signal only — not a legal determination, sanctions certification, compliance clearance, or legal advice. Free during launch.

輸入結構描述

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string",
      "description": "Full name of the person or organization to screen (2-200 characters).",
      "minLength": 2,
      "maxLength": 200
    },
    "dob": {
      "type": "string",
      "description": "Date of birth as YYYY-MM-DD (optional; must be a real past date).",
      "pattern": "^\\d{4}-\\d{2}-\\d{2}$"
    },
    "nationality": {
      "type": "string",
      "description": "ISO 3166-1 alpha-2 country code, e.g. \"DE\" (optional).",
      "pattern": "^[A-Za-z]{2}$"
    }
  },
  "required": [
    "name"
  ],
  "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1 個工具