milestone_update · Trac MCP: Risk & Policy

WHAT IT DOES

What milestone_update does on Trac

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

WHY IT NEEDS A POLICY

Why milestone_update needs a policy

This tool modifies existing milestone data (due dates, completion status, descriptions) but does not delete or irreversibly destroy information. The changes are reversible through subsequent updates. While it requires TICKET_ADMIN permission, the core capability is data modification (Write category), not deletion (Destructive) or execution of arbitrary code (Execute).

From the tool's definition Tool name 'milestone_update' and description 'Update an existing milestone' explicitly performs modification of data. The attributes (due, completed, description) are reversible changes to milestone properties.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

milestone_update Rate-limited

milestone_update 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": {
    "milestone_update": {
      "limits": [
        {
          "counter": "milestone_update_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 Trac, so you can run agents against it safely.

FAQ

Questions about milestone_update

What does the milestone_update tool do? +

Update an existing milestone. Requires TICKET_ADMIN permission. Attributes: due (ISO 8601 date), completed (ISO 8601 date or 0), description (string). It is categorised as a Write tool in the Trac MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on milestone_update? +

Register the Trac MCP server in PolicyLayer and add a rule for milestone_update: 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 Trac. Nothing to install.

What risk level is milestone_update? +

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

Can I rate-limit milestone_update? +

Yes. Add a rate_limit block to the milestone_update 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 milestone_update completely? +

Set action: deny in the PolicyLayer policy for milestone_update. 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 milestone_update? +

milestone_update is provided by the Trac MCP server (nerpatech/trac-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.