AI agents call listen_for_yes_no to retrieve information from Voice MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads and processes audio input (speech-to-text interpretation) to extract a boolean response. It performs no state changes, no code execution, no financial operations, and no destructive actions. The only output is a yes/no classification of user input, making it a straightforward Read operation.
From the tool's definition Tool records audio and interprets it as yes/no without creating, modifying, executing, or deleting data. The description indicates it 'record[s] a short audio response and interpret[s] it' — purely input/analysis operations with no side effects.
Attacks that exploit this kind of access
Record a short audio response and interpret it as yes or no. It is categorised as a Read tool in the Voice MCP MCP Server, which means it retrieves data without modifying state.
Register the Voice MCP server in PolicyLayer and add a rule for listen_for_yes_no: 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 MCP. Nothing to install.
listen_for_yes_no 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 listen_for_yes_no 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 listen_for_yes_no. 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.
listen_for_yes_no is provided by the Voice MCP server (jochiang/voice-mcp). 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 →