Return the current recording/analyzing/done state for a voice session.
AI agents call voice_capture_status 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 only retrieves state information about an ongoing or completed voice session without modifying, executing external operations, or causing irreversible changes. It is purely informational and safe to expose to AI agents.
From the tool's definition Tool returns current state ('recording/analyzing/done') with no side effects or modifications. Description indicates it is a status query operation: 'Return the current recording/analyzing/done state'.
Attacks that exploit this kind of access
Return the current recording/analyzing/done state for a voice session. 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 voice_capture_status: 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.
voice_capture_status 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 voice_capture_status 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 voice_capture_status. 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.
voice_capture_status 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 →