MiniMax-AI/MiniMax-MCP

Official MiniMax Model Context Protocol (MCP) server that enables interaction with powerful Text to Speech, image generation and video generation APIs.

What it solves

This project provides an official Model Context Protocol (MCP) server that allows AI clients (such as Claude Desktop, Cursor, and Windsurf) to directly access MiniMax's generative AI capabilities. It bridges the gap between LLM interfaces and specialized APIs for high-quality audio, video, and image generation.

How it works

The server implements the MCP standard, enabling it to act as a tool-provider for LLMs. It supports two transport methods: stdio for local execution and SSE (Server-Sent Events) for cloud or network-based deployments. Once configured with an API key and host, the LLM can call specific tools to trigger generative tasks.

Who it’s for

Developers and AI power users who use MCP-compatible IDEs or chat interfaces and want to integrate professional-grade text-to-speech, voice cloning, and media generation directly into their AI-assisted workflows.

Highlights

  • Multimodal Generation: Supports text-to-audio, text-to-image, and text-to-video generation.
  • Advanced Audio Tools: Includes voice cloning and a voice_design tool to create custom voices from text descriptions.
  • Music Creation: Integrated music generation powered by the music-1.5 model.
  • Video Control: Supports the MiniMax-Hailuo-02 model with adjustable duration (6s/10s) and resolution (768P/1080P).
  • Broad Compatibility: Works with major MCP clients like Claude Desktop, Cursor, Windsurf, and OpenAI Agents.