Return the most recent voice capture state, transcript, and feedback.
AI agents call latest_voice_capture 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 queries and retrieves previously captured voice coaching data. It performs a read-only operation with no side effects: it neither modifies state, executes commands, deletes data, nor commits financial transactions. The blast radius of misuse is minimal—an agent could only access feedback that was already generated.
From the tool's definition Tool returns the most recent voice capture state, transcript, and feedback — purely retrieves existing data with no modification, deletion, or execution of external operations.
Attacks that exploit this kind of access
Return the most recent voice capture state, transcript, and feedback. 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 latest_voice_capture: 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.
latest_voice_capture 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 latest_voice_capture 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 latest_voice_capture. 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.
latest_voice_capture 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 →