Agentic Diaries Audit

io.github.kandikandikandiPublished by GitHub account kandikandikandiv0.1.0Updated Oct 24, 2026

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

The publisher's own server: audit.domains - Domain Valuation

VerifiedStreamable HTTPWeb executableProductivity & Workflow Business & Commerce

Server details

Identifier: io.github.kandikandikandi/behavioral-audit
Transport: Streamable HTTP
Runtime: Web executable
Trust: Verified
Published: Sep 16, 2026

Security note

MCP servers receive tool arguments from a conversation and may perform external actions. Review what a server can do before you enable it, and give it only the access it needs.

The registry verified the GitHub account kandikandikandi for this listing. That does not show the account is the product's maker.

SourceWeft's checks cover whether the listing is complete and the endpoint answered; they do not review the server's code or what its tools do.

Add a badge to your README

Show readers this MCP server is listed on SourceWeft. The badge links to this page.

[![Listed on SourceWeft](https://sourceweft.com/badge/mcp/io.github.kandikandikandi%2Fbehavioral-audit.svg)](https://sourceweft.com/mcp/io.github.kandikandikandi%2Fbehavioral-audit?utm_source=readme&utm_medium=badge)

Overview

AI-generated overview

A hosted MCP tool that checks a draft customer support reply for policy disclosures it should have made but did not.

What you can do: Check a draft support reply against what the customer said, before it is sent, using the disclosure_check tool with the customer message and the draft reply as input. Receive a verdict of pass or gap. On a gap, get each missed policy named along with the line that should have been included, such as a refund window, auto-renewal, retention offer or warranty term. It only detects and suggests; it does not rewrite the reply, send anything, or keep the message beyond the check.
When to use it: Useful for support agents or teams who want a quick pre-send check that a reply proactively surfaces relevant policies, for example when a customer cancels and may still qualify for a refund. Best suited to single-message reviews rather than full conversation handling.
Requirements: A remote MCP endpoint added to the client configuration over HTTP; no login, signup, API key or environment variables are needed. The client must support HTTP transport, and a restart or reconnect may be needed for the tool to appear.

Before you install

The customer message and draft reply are sent to a third-party hosted service for checking. The check only flags gaps and does not guarantee a reply is complete or correct, so review before sending. It does not send or modify anything itself.

Installation

In SourceWeft

Open Agentic Diaries Audit in the dashboard and add it to a workspace.
Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.kandikandikandi%2Fbehavioral-audit/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "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:

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"    }  }}

{  "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."}

{  "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."    }  ]}

{  "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.

Source: README.md at commit 5c03950

Tools

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.

Parametersdraft_replyrequiredcustomer_messagerequired

Version history

v0.1.0LatestSep 16, 2026

Score

90% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.