comet_stop · Comet MCP: Risk & Policy

WHAT IT DOES

What comet_stop does on Comet

AI agents invoke comet_stop to trigger actions in Comet. 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 comet_stop needs a policy

This tool executes a control operation (stopping a running task) on an external browser agent. While stopping is less risky than creating side effects, it still represents an actionable command that affects the state of an external system.

From the tool's definition Tool name 'comet_stop' and description 'Stop the current agent task if it' indicates the tool triggers termination of an ongoing operation in an isolated browser instance.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

comet_stop Rate-limited

comet_stop 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": {
    "comet_stop": {
      "limits": [
        {
          "counter": "comet_stop_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 Comet, so you can run agents against it safely.

FAQ

Questions about comet_stop

What does the comet_stop tool do? +

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

How do I enforce a policy on comet_stop? +

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

What risk level is comet_stop? +

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

Can I rate-limit comet_stop? +

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

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

comet_stop is provided by the Comet MCP server (simplicianokelly52/comet_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.