close_bug · Zentao MCP: Risk & Policy

WHAT IT DOES

What close_bug does on Zentao

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

WHY IT NEEDS A POLICY

Why close_bug needs a policy

This tool modifies bug state reversibly (close vs. open), which is characteristic of Write operations. It is not Destructive because closing does not delete or irreversibly erase data. It is not Execute because it does not run external commands or code. Severity is medium because misuse could incorrectly close important bugs affecting workflows, but the effect is easily reversible by reopening.

From the tool's definition The tool 'close_bug' closes a bug by ID. Closing is a state change to bug records—a reversible modification (bugs can typically be reopened in bug tracking systems). The description explicitly states it modifies a bug's status.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

close_bug Rate-limited

close_bug 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": {
    "close_bug": {
      "limits": [
        {
          "counter": "close_bug_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 Zentao, so you can run agents against it safely.

FAQ

Questions about close_bug

What does the close_bug tool do? +

Close one bug by ID. It is categorised as a Write tool in the Zentao MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on close_bug? +

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

What risk level is close_bug? +

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

Can I rate-limit close_bug? +

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

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

close_bug is provided by the Zentao MCP server (@aipper/zentao-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.