LeakGuard
Find and redact leaked secrets, wallet keys and PII before an AI agent sends text.
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
~249Token(工具定義)
~714 B典型回應大小
極小的注意力影響(128k 上下文的 0.19%)
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": {
"leakguard": {
"command": "npx",
"args": [
"@agentgate-builder/leakguard"
]
}
}
}可執行的套件
npm@agentgate-builder/leakguard
0.1.0stdio遠端端點
https://api.youraitools.co/leakguard/mcpstreamable-http它能做什麼
工具清單
工具(1)
🟢 唯讀🟡 寫入🔴 刪除⚪ 未知
🟢scan_for_leaks(text)
Check text BEFORE your agent sends it to an LLM, tool, log or webhook: finds crypto wallet keys (BIP39 seed phrases with checksum, EVM/Solana private keys, WIF, xprv), API secrets (GitHub, AWS, Stripe, OpenAI, Anthropic, Slack, Telegram, npm, JWT, PEM) and PII (cards, IBAN, SSN, email, phone). Free preview tier: verdict, safe_to_send and counts by type (text up to 8192 bytes). Redacted text: paid x402 endpoint /v1/lite ($0.005); JSON payloads and live balances of wallets whose keys leaked: /v1/scan ($0.02).
輸入結構描述
{
"type": "object",
"properties": {
"text": {
"type": "string",
"description": "Text to check before it is sent (prompt, tool arguments, log, message, file content). POST /v1/scan also accepts {\"json\": <any JSON payload>}."
}
},
"required": [
"text"
]
}社群
證據
近期觀測
已驗證未記錄版本1 個工具