Tier-1 Ticket Deflection Agent

Name: Tier-1 Ticket Deflection Agent
Availability: InStock
Author: Kata Team

Answers the same twenty support questions from your knowledge base, and escalates everything else.

Customer Service Retail Conversational Support (Chatbots)Returns & Order Management Ticket Routing & Triage Sentiment & Escalation Knowledge Base Automation @katateam

Before you connect: what this agent would do

A preview derived from this agent’s definition — not a live run. Nothing runs and no key is sent until you connect. FindAgent runs it on the hosted connection.

Tools it can use (8)

get_ticketRead-only
Fetch a ticket's subject, status, priority, requester, tags, and channel.
Reaches: {subdomain}.zendesk.com
Uses your Zendesk API credential.
list_ticket_commentsRead-only
Fetch the full comment thread on a ticket, including which comments are public.
Reaches: {subdomain}.zendesk.com
Uses your Zendesk API credential.
search_help_centerRead-only
Search published Help Center articles for a phrase and return ranked matches.
Reaches: {subdomain}.zendesk.com
Uses your Zendesk API credential.
get_articleRead-only
Fetch the full body of one Help Center article so it can be read before citing it.
Reaches: {subdomain}.zendesk.com
Uses your Zendesk API credential.
search_solved_ticketsRead-only
Search previously solved tickets to see how a human answered the same question before.
Reaches: {subdomain}.zendesk.com
Uses your Zendesk API credential.
compose_deflection_replyRead-only
Turn a retrieved article into a short cited customer reply, or refuse when the source does not answer the question.
post_public_replyCan change data
Add the approved reply to the ticket as a public comment visible to the customer.
Reaches: {subdomain}.zendesk.com
Uses your Zendesk API credential.
escalate_to_humanCan change data
Add a private internal note explaining what was searched and why it was insufficient, then route the ticket to a group.
Reaches: {subdomain}.zendesk.com
Uses your Zendesk API credential.

Credentials it will ask for (1)

Zendesk API credential
Only ever sent to: zendesk.com
Format: Paste the Base64 encoding of “id:token” (e.g. your email and API token joined by a colon), not the raw token. Many tools show this ready-made as your “Basic auth” value.

Safety rails that guard it

Every result is scanned for leaked secrets and prompt-injection before it reaches you — a check no agent can turn off.
These personal details are removed from your input before the agent sees them: Credit card, IBAN, National ID.
A request larger than 60,000 characters is rejected before it runs.
get_ticketRate limited to 300/hour.Safe to retry automatically if a run is interrupted.
get_articleRate limited to 300/hour.Safe to retry automatically if a run is interrupted.
escalate_to_humanRate limited to 120/hour.
post_public_replySensitive — it is flagged and needs an explicit confirmation before it runs.Rate limited to 60/hour.Runs only after get_article has run first.
search_help_centerRate limited to 300/hour.Safe to retry automatically if a run is interrupted.
list_ticket_commentsRate limited to 300/hour.Safe to retry automatically if a run is interrupted.
search_solved_ticketsRate limited to 200/hour.Safe to retry automatically if a run is interrupted.
compose_deflection_replyRate limited to 200/hour.Safe to retry automatically if a run is interrupted.

How FindAgent keeps agents safe

Run locally

This MCP server runs on your own machine — FindAgent only points you at it. Run the command below, then add it to your MCP client. Nothing is hosted or proxied on our side.

terminal

npx -y @findagent/mcp run

Add it to your MCP client

Paste this into your client config (e.g. claude_desktop_config.json or a Cursor mcp.json), then restart the client.

mcp client config

{
  "mcpServers": {
    "tier-1-ticket-deflection-agent": {
      "command": "npx",
      "args": [
        "-y",
        "@findagent/mcp",
        "run"
      ]
    }
  }
}

What you'll need — and where to get it

This agent will ask you for the following. You enter them when you connect — they're encrypted and never shared with the creator.

Zendesk API credential
Base64 of 'your-agent-email/token:YOUR_API_TOKEN' — encode it yourself before pasting; the runtime only adds the Basic prefix. Create the token under Admin Center > Apps and integrations > Zendesk API. An agent account is enough; it does not need admin.
Get this from zendesk.com's account or API settings.
Paste the value as a single line.
Only sent to: zendesk.com

Requirements

This server requires authentication — see the description for how to get a key.

Get this agent

Free

Add the hosted gateway to Claude, ChatGPT, Cursor or any MCP client. Nothing installs on your machine.

https://mcp.findagent.cloud/agents/tier-1-ticket-deflection-agent

View setup

What we can prove

Ships no executable code. FindAgent’s trusted runtime performs only the actions this agent declares — nothing it wrote runs on your machine or ours.
Any key you connect is bound to its destination — it is only ever sent to zendesk.com, and is dropped if a request tries to redirect it elsewhere.
Every result is scanned for leaked secrets and prompt-injection before it reaches you — a check no listing can turn off.
Some tools can create, change, or delete data in your connected accounts — your AI client asks you to confirm before a change runs.
Passed an automated security scan and a human review before it could be published.

These are facts derived from the manifest, not a score and not a badge.

Agent details