cast_stop · Kef MCP: Risk & Policy

WHAT IT DOES

What cast_stop does on Kef

AI agents invoke cast_stop to trigger actions in Kef. 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 cast_stop needs a policy

This tool triggers an external operation (stopping playback and closing the receiver) on a networked physical device. While not destructive (playback can be resumed) or financial, it is Execute-category because it performs an action with real-world effects on the speaker's state.

From the tool's definition Tool name is 'cast_stop' with description 'Stop Cast playback on the KEF and close the Cast receiver.' This executes a command on a KEF speaker device via local network to stop playback and terminate the Cast receiver session.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

cast_stop Rate-limited

cast_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": {
    "cast_stop": {
      "limits": [
        {
          "counter": "cast_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 Kef, so you can run agents against it safely.

FAQ

Questions about cast_stop

What does the cast_stop tool do? +

Stop Cast playback on the KEF and close the Cast receiver. It is categorised as a Execute tool in the Kef MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on cast_stop? +

Register the Kef MCP server in PolicyLayer and add a rule for cast_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 Kef. Nothing to install.

What risk level is cast_stop? +

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

Can I rate-limit cast_stop? +

Yes. Add a rate_limit block to the cast_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 cast_stop completely? +

Set action: deny in the PolicyLayer policy for cast_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 cast_stop? +

cast_stop is provided by the Kef MCP server (nqrwhal/kef-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.