Get list of available voices with their capabilities and supported features
AI agents call get_voices to retrieve information from Advanced TTS MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns information about available voices and their capabilities. It performs no modifications, deletions, or external operations. The retrieval of static configuration or capability metadata poses minimal risk; an AI agent misusing this tool would only retrieve harmless voice metadata, with no blast radius beyond information disclosure of already-public TTS service features.
From the tool's definition Tool name is 'get_voices' and description states it gets a 'list of available voices' — a pure retrieval operation with no side effects.
Attacks that exploit this kind of access
Get list of available voices with their capabilities and supported features. It is categorised as a Read tool in the Advanced TTS MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Advanced TTS MCP Server MCP server in PolicyLayer and add a rule for get_voices: 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 Advanced TTS MCP Server. Nothing to install.
get_voices 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 get_voices 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 get_voices. 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.
get_voices is provided by the Advanced TTS MCP Server MCP server (samihalawa/advanced-tts-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 →