MCP Catalogs
HomeMiniMax-MCP screenshot

MiniMax-MCP

by MiniMax-AI·1,476·Score 56

Official MCP server for MiniMax's Text-to-Speech, image and video generation APIs.

ai-llmmediadeveloper-tools
261
Forks
31
Open issues
this month
Last commit
2d ago
Indexed

Overview

MiniMax-MCP is the official Model Context Protocol server that enables interaction with MiniMax's powerful Text-to-Speech, image generation, and video generation APIs. It allows MCP clients like Claude Desktop, Cursor, and Windsurf to generate speech, clone voices, create videos, and produce images. The server supports both stdio and SSE transport methods, making it suitable for local deployment or cloud-based solutions. It provides a comprehensive set of tools including text_to_audio, voice_clone, generate_video, text_to_image, and music_generation.

Try asking AI

After installing, here are 5 things you can ask your AI assistant:

you:Create voiceovers for videos and presentations using MiniMax's TTS API
you:Generate custom voices for AI assistants with voice cloning capabilities
you:Produce marketing videos and visual content directly from AI prompts
you:What should I do if I get an 'invalid api key' error?
you:How do I fix 'spawn uvx ENOENT' error?

When to choose this

Choose this when you need multimedia generation capabilities (speech, images, videos) integrated into your MCP client workflow and you're already using MiniMax's API.

When NOT to choose this

Avoid if you need open-source alternatives, want to avoid vendor lock-in with MiniMax, or need more extensive multimedia editing capabilities beyond generation.

Tools this server exposes

8 tools extracted from the README
  • text_to_audio

    Convert text to audio with a given voice

  • list_voices

    List all voices available

  • voice_clone

    Clone a voice using provided audio files

  • generate_video

    Generate a video from a prompt

  • text_to_image

    Generate an image from a prompt

  • query_video_generation

    Query the result of video generation task

  • music_generation

    Generate a music track from a prompt and lyrics

  • voice_design

    Generate a voice from a prompt using preview text

Comparable tools

elevenlabs-mcpstability-mcpopenai-dall-e-mcp

Installation

Installation

  1. Get your API key from [MiniMax](https://www.minimax.io/platform/user-center/basic-information/interface-key).
  2. Install uv package manager: curl -LsSf https://astral.sh/uv/install.sh | sh
  3. Configure your MCP client with the following settings:

For Claude Desktop:

{
  "mcpServers": {
    "MiniMax": {
      "command": "uvx",
      "args": [
        "minimax-mcp",
        "-y"
      ],
      "env": {
        "MINIMAX_API_KEY": "insert-your-api-key-here",
        "MINIMAX_MCP_BASE_PATH": "local-output-dir-path, such as /User/xxx/Desktop",
        "MINIMAX_API_HOST": "https://api.minimax.io | https://api.minimaxi.com",
        "MINIMAX_API_RESOURCE_MODE": "optional, [url|local], url is default, audio/image/video are downloaded locally or provided in URL format"
      }
    }
  }
}

For Cursor, add the same configuration in Cursor -> Preferences -> Cursor Settings -> MCP -> Add new global MCP Server.

FAQ

What should I do if I get an 'invalid api key' error?
Ensure your API key and API host are regionally aligned. Use https://api.minimax.io for Global region and https://api.minimaxi.com for Mainland region, with corresponding keys from each platform.
How do I fix 'spawn uvx ENOENT' error?
Check the absolute path of uvx by running 'which uvx' in your terminal, then update your configuration with this full path instead of just 'uvx'.

Compare MiniMax-MCP with

GitHub →

Last updated · Auto-generated from public README + GitHub signals.