AI agents call list_voices to retrieve information from Retellai without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only retrieval of voice options from the Retell AI service. It has no ability to create, modify, delete, execute commands, or perform financial operations. The blast radius of misuse is minimal—an agent could only enumerate available voices, which is informational data with no operational impact.
From the tool's definition Tool name 'list_voices' and description 'Lists all available Retell voices' indicate a query operation that retrieves voice data without modification or side effects.
Attacks that exploit this kind of access
Lists all available Retell voices. It is categorised as a Read tool in the Retellai MCP Server, which means it retrieves data without modifying state.
Register the Retellai MCP server in PolicyLayer and add a rule for list_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 Retellai. Nothing to install.
list_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 list_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 list_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.
list_voices is provided by the Retellai MCP server (@abhaybabbar/retellai-mcp-server). 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 →