#76 · Primary category: AI Gateway & API Infrastructure

MiniMax-MCP

image-generation image-to-video mcp mcp-server mcp-tools text-to-image text-to-speech text-to-video video-generation voice-cloning

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

Project last updated:08/20/26

GitHub Stars

1.6K

Forks

279

Contributors

11

License

MIT

Why we included this project

MiniMax ships an official Model Context Protocol server that turns its hosted speech, image, and video generation APIs into tools any MCP-compatible assistant can call. Point it at Claude Desktop, Cursor, Windsurf, or OpenAI Agents and you get text-to-speech, voice cloning, prompt-to-image, text-to-video, and music generation without hand-writing HTTP integrations. The server handles transport over stdio or SSE, saves generated audio, images, and video to local paths, and respects regional API hosts so keys and endpoints stay consistent. For teams already living inside an MCP-capable agent or IDE, this cuts the wiring-up work and lets generation results land directly in the assistant's workflow.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category