list_audio_devices
AI agents call list_audio_devices to retrieve information from Claude Voice Commands without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or enumerates available audio devices without side effects. It performs a read-only query of system audio hardware configuration. No data is modified, deleted, or executed. The empty description lowers confidence slightly, but the name and server context strongly suggest a passive enumeration operation typical of audio setup utilities.
From the tool's definition Tool name 'list_audio_devices' indicates retrieval of audio device information with no modification capability. Server context shows this is part of a voice control system where listing devices is a prerequisite query operation.
Attacks that exploit this kind of access
list_audio_devices. It is categorised as a Read tool in the Claude Voice Commands MCP Server, which means it retrieves data without modifying state.
Register the Claude Voice Commands MCP server in PolicyLayer and add a rule for list_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 Claude Voice Commands. Nothing to install.
list_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 list_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 list_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.
list_audio_devices is provided by the Claude Voice Commands MCP server (jwitcoff/claude_chat). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →