mmx-mcp-server

Overview

mmx-mcp-server is a unified Model Context Protocol server that wraps MiniMax's comprehensive AI capabilities into MCP tools. It supports text generation, web search, image understanding, image generation, speech synthesis, video creation, music generation, and quota checking. The server provides a clean interface to access MiniMax's API through MCP, with clear configuration options for API keys and output directories.

Try asking AI

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

• mmx_search

  网页搜索

  Try:帮我搜索 MiniMax 的最新新闻Try:搜索关于人工智能的最新发展
• mmx_vision_describe

  图像理解（支持自定义分析指令，如 UI critique）

  Try:分析一下这个 UI 设计图，给出优化建议Try:描述这张图片中的场景和细节
• mmx_text_chat

  文本对话（支持 system prompt、JSON 模式）

  Try:回答一下关于人工智能的问题Try:以 JSON 格式列出三个最新的科技趋势
• mmx_image_generate

  图像生成（支持 out 指定路径）

  Try:生成一张赛博朋克风格的城市夜景图Try:创建一个可爱的卡通角色形象
• mmx_speech_synthesize

  语音合成 TTS（支持 out 指定路径）

  Try:把这段文字转成语音Try:用女声朗读这段新闻稿
• mmx_video_generate

  视频生成（支持 out 指定路径）

  Try:生成一个10秒的产品介绍短视频Try:创建一个关于太空探索的动画片段
• mmx_music_generate

  音乐生成（支持 out 指定路径）

  Try:创作一段轻松的背景音乐Try:生成一个电子舞曲片段
• mmx_quota_show

  查看配额

  Try:查看我的 MiniMax API 使用配额Try:显示剩余的调用次数

Comparable tools

Installation

npm install -g mmx-cli
git clone https://github.com/zth0828/mmx-mcp-server.git
cd mmx-mcp-server
npm install
npm run build

{
  "mcpServers": {
    "mmx": {
      "command": "node",
      "args": ["/path/to/mmx-mcp-server/dist/index.js"],
      "env": {
        "MINIMAX_API_KEY": "sk-xxxxx"
      }
    }
  }
}

FAQ

How do I configure the API key?

You can set the MINIMAX_API_KEY environment variable in your MCP server configuration, pass it as a command line argument, or authenticate through the mmx CLI with 'mmx auth login --api-key'.

Where are generated files saved?

By default, files are saved in subdirectories of the current working directory (mmx_image, mmx_video, etc.). You can customize this with the MMX_OUTPUT_DIR environment variable.

Compare mmx-mcp-server with