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
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
證據
近期觀測
已驗證未記錄版本1 個工具