Critical Risk →

whisper_uninstall

Uninstall whisper.cpp and optionally remove models and data. This tool will: 1. Stop any running Whisper service 2. Remove service configurations (launchd/systemd) 3. Remove the whisper.cpp installation 4. Optionally remove downloaded models 5. Optionally remove all Whisper-related data Args: rem...

How to control whisper_uninstall ↓

What whisper_uninstall does on Voice Mode

AI agents call whisper_uninstall to permanently remove resources in Voice Mode — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.

Critical Risk

Why whisper_uninstall needs a policy

This tool performs irreversible deletion of software installations, service configurations, downloaded models, and user data (logs, transcriptions). These actions cannot be undone without reinstalling and reconfiguring from scratch.

From the tool's definition Tool description explicitly states it will "Uninstall whisper.cpp", "Remove service configurations", "Remove the whisper.cpp installation", and "Optionally remove downloaded models" and "remove all Whisper data including logs and transcriptions".

Documented attack patterns abuse exactly the kind of access whisper_uninstall gives an agent:

How to control whisper_uninstall

PolicyLayer is an MCP gateway — it sits between your AI agents and Voice Mode, and nothing reaches the server without passing your rules. This is the rule we recommend for whisper_uninstall:

policy.json
{
  "version": "1",
  "default": "deny",
  "hide": [
    "whisper_uninstall"
  ]
}

whisper_uninstall disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.

  1. Create a free account and register Voice Mode — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
RESTRICT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about whisper_uninstall

What does the whisper_uninstall tool do? +

Uninstall whisper.cpp and optionally remove models and data. This tool will: 1. Stop any running Whisper service 2. Remove service configurations (launchd/systemd) 3. Remove the whisper.cpp installation 4. Optionally remove downloaded models 5. Optionally remove all Whisper-related data Args: remove_models: Also remove downloaded Whisper models (default: False) remove_all_data: Remove all Whisper data including logs and transcriptions (default: False) Returns: Dictionary with uninstall status and details. It is categorised as a Destructive tool in the Voice Mode MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.

How do I enforce a policy on whisper_uninstall? +

Register the Voice Mode MCP server in PolicyLayer and add a rule for whisper_uninstall: 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 Voice Mode. Nothing to install.

What risk level is whisper_uninstall? +

whisper_uninstall is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit whisper_uninstall? +

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

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

whisper_uninstall is provided by the Voice Mode MCP server (mbailey/voicemode). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Voice Mode tool call.

Start from Voice Mode, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

Free to start. No card required.

25 Voice Mode tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.