ElevenLabs MCP Server

Instructions

Implementation Reference

• elevenlabs_mcp/server.py:455-480 (handler)

  The handler function for the 'search_voices' tool, decorated with @mcp.tool for registration. It performs the search using the ElevenLabs client API and maps results to McpVoice models.
  @mcp.tool( description=""" Search for existing voices, a voice that has already been added to the user's ElevenLabs voice library. Searches in name, description, labels and category. Args: search: Search term to filter voices by. Searches in name, description, labels and category. sort: Which field to sort by. `created_at_unix` might not be available for older voices. sort_direction: Sort order, either ascending or descending. Returns: List of voices that match the search criteria. """ ) def search_voices( search: str | None = None, sort: Literal["created_at_unix", "name"] = "name", sort_direction: Literal["asc", "desc"] = "desc", ) -> list[McpVoice]: response = client.voices.search( search=search, sort=sort, sort_direction=sort_direction ) return [ McpVoice(id=voice.voice_id, name=voice.name, category=voice.category) for voice in response.voices ]
• elevenlabs_mcp/model.py:5-9 (schema)

  Pydantic BaseModel defining the structure of voice objects returned by the search_voices tool.
  class McpVoice(BaseModel): id: str name: str category: str fine_tuning_status: Optional[Dict] = None