MCPOfficialMiniMax
MiniMax MCP
Speech synthesis, voice cloning and voice design, plus images and video from MiniMax models.
MiniMax’s official server (Python, launched with uvx) provides tools for text-to-speech with a choice of voices, cloning a voice from samples and designing a voice from a description, as well as generating images and Hailuo videos. It requires an API key, and the API host must match the key’s region (global or mainland China); API calls may be billed.
Installation
Manual install
{"mcpServers":{"MiniMax":{"command":"uvx","args":["minimax-mcp","-y"],"env":{"MINIMAX_API_KEY":"<API_KEY>","MINIMAX_MCP_BASE_PATH":"<OUTPUT_DIR>","MINIMAX_API_HOST":"https://api.minimax.io"}}}}Details
- Works in
- Claude, Cursor, Windsurf
- Transport
- local
- License
- MIT
- Tasks
- Audio, Video, Graphics
- Rating
- Source
- github.com/MiniMax-AI/MiniMax-MCP (opens in a new tab)
Tags
- minimax
- tts
- speech synthesis
- voice cloning
- voiceover
- hailuo
A pack is your own set of skills and MCP servers. sciver loads it in your AI with one command.