MiniMax MCP is an official server implementing the Model Context Protocol. It provides a gateway to interact with MiniMax's advanced APIs for generating speech, video, and images.
To begin, you need a MiniMax API key and the uv Python package manager installed. After obtaining these, configure your MCP client—such as Claude Desktop or Cursor—to connect to the MiniMax server.
Key capabilities include enabling Text-to-Speech, supporting video and image generation, and allowing voice cloning. It integrates seamlessly with various MCP clients.
Use cases range from generating speech for news segments and cloning voices for personalized audio, to creating educational videos and images from text descriptions.
Regarding compatibility, it works with clients like Claude Desktop and Cursor that support MCP. Please note, usage of the MiniMax APIs may incur costs based on your consumption. For setup, follow the configuration instructions specific to your client in the provided documentation.
{
"mcpServers": {
"MiniMax": {
"command": "uvx",
"args": [
"minimax-mcp"
],
"env": {
"MINIMAX_API_KEY": "<insert-your-api-key-here>",
"MINIMAX_MCP_BASE_PATH": "<local-output-dir-path>",
"MINIMAX_API_HOST": "https://api.minimaxi.chat",
"MINIMAX_API_RESOURCE_MODE": "<optional, [url|local], url is default, audio/image/video are downloaded locally or provided in URL format>"
}
}
}
}