Support Triage — MCP

Classify an inbound message, propose a first reply hold, and flag escalation — human sends. (MCP-oriented tool + prompt pack (read-only first).)

Id: mcp/support-triage · Slug: support-triage · Status: Untested · Untested on this machine — recipe reviewed for safety (no secrets, no destructive commands, no auto-spend). Mark tested after you run it locally.

What is this

MCP for MCP. Classify an inbound message, propose a first reply hold, and flag escalation — human sends. (MCP-oriented tool + prompt pack (read-only first).)

How this runtime fits

This MCP pack is an MCP integration / tool-enabled agent surface for the parent AI Team. Multi-agent language applies only when a host actually composes multiple agents around these tools.

Parent AI Team: support-triage · What is an AI Team?

What it does

Classify an inbound message, propose a first reply hold, and flag escalation — human sends. (MCP-oriented tool + prompt pack (read-only first).)

Who for

Builders working on Support jobs who can run MCP themselves.

Need to run

You will run this locally or on infra you control.
No production credentials in prompts or committed files.
MCP-aware client
Ability to allowlist tools

How to use

Review server_hints.md and implement only allowlisted read-only tools.
Load prompt.md as the client system prompt.
Run one Example in query with tools off; then enable library_search only.
Confirm path allowlist before any file read tool.

Limitations

Not a substitute for professional legal, medical, or investment advice.
Outputs can be wrong; human review required before publish or spend.
Stage-1 Library items are free recipes — marketplace ready-to-use teams remain separate.
Local models may omit sections; re-prompt once if needed.
No harvesting of personal data beyond what the operator pasted.

Test status

Status: Untested · Untested on this machine — recipe reviewed for safety (no secrets, no destructive commands, no auto-spend). Mark tested after you run it locally.

Files

server_hints.md — MCP server/tool design notes
prompt.md — Client system prompt when tools are available

Full prompt / config / code

# MCP pack — Support Triage

## prompt.md (client)
You are a support triage assistant. Goal: classify and draft a hold reply.

RULES:
- Human sends the message. You do not send email/chat.
- Never ask for passwords, seed phrases, or full card numbers.
- Escalate billing disputes and safety issues.
- Keep the hold reply short and kind.

OUTPUT:
1) Category + urgency
2) What we know / need
3) Hold-reply draft
4) Escalate? yes/no + why

## server_hints.md
Expose only read-only tools for stage 1, for example:
- `library_search` — search local catalog snippets the user installed
- `fetch_local_file` — read a path under an allowlisted directory

Tool design rules:
- No tool that sends email, posts to social, or charges payment.
- No tool that reads `~/.ssh`, `.env`, or browser cookie DBs.
- Arguments must be schema-validated; reject path traversal.
- Log tool calls for the human operator.

Example tool schema (illustrative JSON):
```json
{
  "name": "library_search",
  "description": "Search local BotShelf library snippets",
  "inputSchema": {
    "type": "object",
    "properties": {
      "query": {"type": "string", "minLength": 1, "maxLength": 200}
    },
    "required": ["query"]
  }
}
```

Wire this pack into an MCP-aware client with tools disabled until the allowlist is reviewed.

Example in

From: user@example.com
Subject: charged twice?
Body: I see two USDT sends. Order #1842. Need help.

Example out

Category: billing / duplicate payment | urgency: high
Know: order #1842, two USDT sends claimed
Need: txids, amounts, times
Hold-reply: Thanks — please reply with both txids…
Escalate: yes — payment mismatch

Model / runtime notes

Protocol-level pack. Prefer read-only tools. Never ship credentials inside MCP configs.

Canonical Team

Parent: support-triage · implementation_id: mcp/support-triage

GitHub source

teams/support-triage/mcp · commit eb87e8e049fdf9908e438305ff827c7b617505b5 · license: free-use-at-own-risk

Structural check: PASS · env: structural (structural only — does not set Verified)

Related Library items

Related marketplace Team pages

Soft thematic links only — not identity merges. Marketplace Teams ≠ Library AI Team records.

First Reply Hold (marketplace Team page — separate entity)
Hold Reply Inbox (marketplace Team page — separate entity)