Agentic Diaries Audit

io.github.kandikandikandi由 GitHub 账号 kandikandikandi 发布v0.1.0更新于 Oct 24, 2026

Checks what a support agent knew but did not say against its policies. Free tier, no login.

发布方自己的服务:audit.domains - Domain Valuation

已验证Streamable HTTP可网页运行效率与工作流商业与电商

概览

AI 生成的概览

一个托管式 MCP 工具,用于检查客服回复草稿是否遗漏了本应主动告知客户的策略信息。

可以做什么
使用 disclosure_check 工具,输入客户原话和回复草稿,在发送前检查草稿是否遗漏应披露内容。返回 pass 或 gap 的判定结果。若为 gap,会列出每条被遗漏的策略以及本应写入的说明,例如退款期限、自动续费、挽留优惠或保修条款。它只做检测和建议,不会改写回复、不会发送任何内容,也不会在检查后保留消息。
适用场景
适合客服人员或团队在发送前快速确认回复是否主动说明了相关策略,例如客户取消订阅且仍符合退款条件时。更适合单条消息的审查,而非完整对话处理。
运行要求
需在客户端配置中以 HTTP 方式添加远程 MCP 端点;无需登录、注册、API 密钥或环境变量。客户端需支持 HTTP 传输,可能需要重启或重新连接后工具才会出现。
安装前请注意
客户消息和回复草稿会被发送到第三方托管服务进行检查。该检查只标记遗漏,不保证回复完整或正确,发送前仍需人工复核。它本身不会发送或修改任何内容。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Agentic Diaries Audit,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Web executable,通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

交给智能体安装

把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体,或 SourceWeft 对话中。智能体会读取该服务器的安装指南,先向你展示发布者、端点和登录方式,经你同意后再把它添加到你的客户端。密钥不会写进任何命令。

阅读 https://sourceweft.com/mcp/io.github.kandikandikandi%2Fbehavioral-audit/install.md,并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前,先告诉我它的发布者、端点和登录方式,等我确认。不要把 API 密钥写进命令或我会提交的文件;问我密钥应从哪里获取。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。

{
  "mcpServers": {
    "agentic-diaries-audit": {
      "type": "http",
      "url": "https://receipts-mcp.vercel.app/api/mcp"
    }
  }
}

README

Behavioral Audit MCP

Check a draft support reply for what it should say and doesn't, before it goes to the customer.

Part of Agentic Diaries. One hosted tool, disclosure_check.

What it does

Give it what a customer said and the reply you are about to send. It flags any should-know policy the customer's situation made relevant that your draft failed to proactively surface: a refund window, an auto-renewal, a retention offer, a warranty term. The knew-but-did-not-say gap, on a single message.

It returns a verdict, pass or gap. On a gap, it names each missed policy and the line that should have been there. It detects and suggests. It does not rewrite your reply, send anything, or keep the message beyond the check.

Install

One line. No login, no signup.

Claude Code:

claude mcp add --transport http behavioral-audit https://receipts-mcp.vercel.app/api/mcp

If you add it mid-session, restart Claude Code (or run /mcp) so the new tool appears.

Claude Desktop (or any MCP client), add to your config:

json
{  "mcpServers": {    "behavioral-audit": {      "type": "http",      "url": "https://receipts-mcp.vercel.app/api/mcp"    }  }}

The tool: disclosure_check

Input:

  • customer_message (string) , what the customer said, verbatim.
  • draft_reply (string) , the reply you are about to send.

Output: a verdict plus, on a gap, the policies your draft left out.

Example

A customer asks to cancel. Your draft confirms it but never mentions the refund window they still qualify for.

Request:

json
{  "customer_message": "I want to cancel my subscription today.",  "draft_reply": "Done, your subscription is cancelled. Sorry to see you go."}

Result:

json
{  "verdict": "gap",  "misses": [    {      "id": "refund_window",      "title": "Refund window",      "suggestion": "You are within your 14-day refund window, so you can still request a refund for this billing period.",      "reason": "The customer is cancelling and qualifies for a refund they were not told about."    }  ]}

A clean reply returns verdict: "pass" with an empty misses list. That means clear to send, not that nothing ran.

来源:README.md,提交 5c03950

工具

1

disclosure_check

Disclosure Check

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.

输入参数draft_reply必填customer_message必填

版本历史

1
  1. v0.1.0最新Sep 16, 2026

评分

已满足适用检查项的 90%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通必需25 分
  • 已声明认证方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分

    请在仓库或注册中心条目中声明许可证。

其他 Audit 集成