search_voice_library
AI agents call search_voice_library to retrieve information from ElevenLabs MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Search operations retrieve and filter data without modification or side effects. The tool appears designed to help users discover available voices from ElevenLabs' library, consistent with Read category semantics (search, list, get, fetch). No evidence suggests it modifies state, executes code, or triggers financial transactions.
From the tool's definition Tool name 'search_voice_library' indicates a query/search operation over available voices. Sibling tools like 'get_voice' and 'list_agents' are clearly Read operations, suggesting this server's search functions are non-destructive queries.
Attacks that exploit this kind of access
search_voice_library. It is categorised as a Read tool in the ElevenLabs MCP Server MCP Server, which means it retrieves data without modifying state.
Register the ElevenLabs MCP Server MCP server in PolicyLayer and add a rule for search_voice_library: 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 ElevenLabs MCP Server. Nothing to install.
search_voice_library 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 search_voice_library 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 search_voice_library. 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.
search_voice_library is provided by the ElevenLabs MCP Server MCP server (nguyendinhsinh361/elevenlabs-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 →