Agentic Diaries Audit
Checks what a support agent knew but did not say against its policies. Free tier, no login.
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
~182Token（工具定義）
~981 B典型回應大小
極小的注意力影響（128k 上下文的 0.14%）
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": {
"behavioral-audit": {
"url": "https://receipts-mcp.vercel.app/api/mcp"
}
}
}遠端端點
https://receipts-mcp.vercel.app/api/mcpstreamable-http它能做什麼
工具清單
工具（1）
🟢 唯讀🟡 寫入🔴 刪除⚪ 未知
🟢disclosure_check(customer_message, draft_reply)
Check a draft support reply for disclosure gaps before sending it. Given what the customer said and the reply you are about to send, it flags any should-know policy the customer's situation made relevant that the draft failed to proactively surface (the knew-but-did-not-say gap). Returns a verdict (pass or gap); on a gap, each missed policy and the line that should have been surfaced. It detects and suggests, it does not rewrite.
輸入結構描述
{
"type": "object",
"properties": {
"customer_message": {
"type": "string",
"description": "What the customer said, verbatim."
},
"draft_reply": {
"type": "string",
"description": "The reply you are about to send."
}
},
"required": [
"customer_message",
"draft_reply"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}社群
證據
近期觀測
已驗證未記錄版本1 個工具
已驗證未記錄版本1 個工具
已驗證未記錄版本1 個工具