stop_task · Greenbone MCP: Risk & Policy

WHAT IT DOES

What stop_task does on GreenboneMCP

AI agents invoke stop_task to trigger actions in GreenboneMCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why stop_task needs a policy

This tool triggers an immediate, observable state change in an external system (halting an active scan). While not destructive (the task/data is not deleted) and not creating or modifying persistent data, it executes a command with side effects that depend on which task is targeted. This fits the Execute category: runs external operations whose effects depend on arguments (in this case, which task_id to stop).

From the tool's definition The tool 'stop_task' stops a running scan task. This performs an external operation against an active vulnerability scanning process managed by Greenbone/OpenVAS. Stopping a task is an actionable control operation that interrupts an ongoing system process.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

stop_task Rate-limited

stop_task stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "stop_task": {
      "limits": [
        {
          "counter": "stop_task_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

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

FAQ

Questions about stop_task

What does the stop_task tool do? +

Stop a running scan task. It is categorised as a Execute tool in the GreenboneMCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on stop_task? +

Register the Greenbone MCP server in PolicyLayer and add a rule for stop_task: 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 GreenboneMCP. Nothing to install.

What risk level is stop_task? +

stop_task is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit stop_task? +

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

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

stop_task is provided by the Greenbone MCP server (matteocolazilli/greenbonemcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.