Download
MiniMax-MCP is the official Model Context Protocol (MCP) server for accessing MiniMax’s multimodal generative APIs from MCP-compatible clients. It acts as a bridge between tools like Claude Desktop, Cursor, Windsurf, OpenAI Agents, and the MiniMax platform, exposing capabilities such as text-to-speech, voice cloning, image generation, text-to-image, video generation, image-to-video, text-to-video, and music generation. The server is written in Python and distributed under the MIT license, with a pyproject.toml and uv-based workflow that makes installation and execution reproducible. Configuration is handled through JSON files that tell MCP clients how to launch the server (typically via uvx minimax-mcp) and which environment variables to use for the API key, host, and output directory. The README carefully explains region-specific API hosts for global and mainland users to avoid invalid-key errors, and documents both local stdio transport and SSE-based network transport modes.
Features
- Official MCP server exposing MiniMax text-to-speech, image, video, and music generation APIs
- Rich tool set including text-to-audio, voice listing, voice cloning, text-to-image, image-to-video, text-to-video, and music generation
- Supports both stdio and SSE transports for local development or cloud deployment
- Region-aware configuration with separate API hosts and keys for global and mainland environments
- Easy integration with MCP clients like Claude Desktop, Cursor, Windsurf, and OpenAI Agents via JSON config
- uv-based Python setup for reproducible installation, dependency management, and command execution
Project Samples
