AI agents call check_audio_devices to retrieve information from Voice Mode without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves system audio device information. It performs read-only enumeration of hardware state with no capability to modify, delete, or execute arbitrary operations. The blast radius if misused by an AI agent is minimal — at most it reveals what audio devices are present on the system, which is low-sensitivity environmental information.
From the tool's definition Tool description explicitly states 'List available audio input and output devices' — a query operation with no side effects.
Documented attack patterns abuse exactly the kind of access check_audio_devices gives an agent:
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 check_audio_devices:
{
"version": "1",
"default": "deny",
"tools": {
"check_audio_devices": {}
}
}check_audio_devices is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
List available audio input and output devices. It is categorised as a Read tool in the Voice Mode MCP Server, which means it retrieves data without modifying state.
Register the Voice Mode MCP server in PolicyLayer and add a rule for check_audio_devices: 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.
check_audio_devices is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the check_audio_devices 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.
Set action: deny in the PolicyLayer policy for check_audio_devices. 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.
check_audio_devices 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.
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.