triage_reject · Tickr MCP: Risk & Policy

WHAT IT DOES

What triage_reject does on Tickr

AI agents use triage_reject to create or update resources in Tickr — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Tickr environment.

PARAMETERS

Parameter	Type	Required	Description
`reason`	string	—	Rejection reason (added as comment)
`project`	string	Yes	Project slug
`ticket_ids`	array	Yes	Array of ticket UUIDs to reject

Parameters from the server's own tool schema.

WHY IT NEEDS A POLICY

Why triage_reject needs a policy

This tool modifies ticket state from triage inbox to cancelled, which is reversible (tickets can typically be reopened or restored in project management systems). It does not permanently delete data (Destructive), execute arbitrary code (Execute), or involve financial transactions (Financial).

From the tool's definition triage_reject moves tickets to cancelled status, which is a state change that modifies ticket data. The description states 'move them to cancelled', indicating the tool updates ticket status/state.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

triage_reject Rate-limited

triage_reject stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "triage_reject": {
      "limits": [
        {
          "counter": "triage_reject_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Tickr, so you can run agents against it safely.

FAQ

Questions about triage_reject

What does the triage_reject tool do? +

Reject tickets from triage inbox — move them to cancelled. It is categorised as a Write tool in the Tickr MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

What parameters does triage_reject accept? +

triage_reject accepts 3 parameters: reason, project, ticket_ids. Required: project, ticket_ids. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on triage_reject? +

Register the Tickr MCP server in PolicyLayer and add a rule for triage_reject: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Tickr. Nothing to install.

What risk level is triage_reject? +

triage_reject is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit triage_reject? +

Yes. Add a rate_limit block to the triage_reject rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block triage_reject completely? +

Set action: deny in the PolicyLayer policy for triage_reject. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides triage_reject? +

triage_reject is provided by the Tickr MCP server (@k-system/tickr-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.