List available audio input devices and verify microphone access.
AI agents call check_mic to retrieve information from Pronunciation & Voice Coach without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs device enumeration and status verification—classic read operations with no side effects, no code execution, and no data modification. The blast radius of misuse is minimal; an agent could at worst learn what audio devices are available on the system, which is low-sensitivity information.
From the tool's definition Tool name 'check_mic' and description 'List available audio input devices and verify microphone access' indicate a query/inspection operation that retrieves system audio device information without modification or execution of arbitrary operations.
Attacks that exploit this kind of access
List available audio input devices and verify microphone access. It is categorised as a Read tool in the Pronunciation & Voice Coach MCP Server, which means it retrieves data without modifying state.
Register the Pronunciation & Voice Coach MCP server in PolicyLayer and add a rule for check_mic: 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 Pronunciation & Voice Coach. Nothing to install.
check_mic 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_mic 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_mic. 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_mic is provided by the Pronunciation & Voice Coach MCP server (pypi:mcp-server-pronunciation). 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 →