Get the current voice provider registry showing all discovered endpoints. Returns a formatted view of all TTS and STT endpoints with their: - Available models - Available voices (TTS only) - Provider type - Last check time - Any recent errors This allows the LLM to see what voice services are cur...
AI agents call voice_registry to retrieve information from Voice Mode without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and displays configuration and status information about voice providers without making any changes to system state or triggering any actions. It is purely informational, similar to list or query operations. The blast radius of misuse is negligible—an attacker gains only visibility into what voice services are configured.
From the tool's definition Tool description explicitly states it 'Get[s] the current voice provider registry' and 'Returns a formatted view' of available endpoints, models, and voices.
Documented attack patterns abuse exactly the kind of access voice_registry gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Voice Mode, and nothing reaches the server without passing your rules. This is the rule we recommend for voice_registry:
{
"version": "1",
"default": "deny",
"tools": {
"voice_registry": {}
}
}voice_registry is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get the current voice provider registry showing all discovered endpoints. Returns a formatted view of all TTS and STT endpoints with their: - Available models - Available voices (TTS only) - Provider type - Last check time - Any recent errors This allows the LLM to see what voice services are currently available. It is categorised as a Read tool in the Voice Mode MCP Server, which means it retrieves data without modifying state.
Register the Voice Mode MCP server in PolicyLayer and add a rule for voice_registry: 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 Mode. Nothing to install.
voice_registry 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_registry 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_registry. 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_registry is provided by the Voice Mode MCP server (mbailey/voicemode). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Voice Mode, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
25 Voice Mode tools catalogued and risk-classified — across an index of 43,000+ MCP servers.