MiniMax Multimodal MCP server

MiniMax MCP JS is a JavaScript/TypeScript implementation of the Model Context Protocol (MCP) that enables powerful AI capabilities including image generation, video generation, and text-to-speech through a simple interface that works with MCP-compatible clients like Claude AI.

Installation

Via Smithery (Automated Installation)

npx -y @smithery/cli install @MiniMax-AI/MiniMax-MCP-JS --client claude

Manual Installation

# Install with pnpm (recommended)
pnpm add minimax-mcp-js

Configuration

Before using MiniMax MCP JS, you'll need to configure it with your API key. Configuration can be done in several ways (listed by priority):

1. Request-Level Configuration

For multi-tenant environments, provide configuration in each request:

{
  "params": {
    "meta": {
      "auth": {
        "api_key": "your_api_key_here",
        "api_host": "https://api.minimaxi.chat",
        "base_path": "/path/to/output",
        "resource_mode": "url"
      }
    }
  }
}

2. Environment Variables

# Required
MINIMAX_API_KEY=your_api_key_here

# Optional
MINIMAX_API_HOST=https://api.minimaxi.chat
MINIMAX_MCP_BASE_PATH=~/Desktop
MINIMAX_RESOURCE_MODE=url

3. Client Configuration

Claude Desktop

Add to Claude > Settings > Developer > Edit Config > claude_desktop_config.json:

{
  "mcpServers": {
    "minimax-mcp-js": {
      "command": "npx",
      "args": [
        "-y",
        "minimax-mcp-js"
      ],
      "env": {
        "MINIMAX_API_HOST": "https://api.minimaxi.chat",
        "MINIMAX_API_KEY": "your-api-key-here",
        "MINIMAX_MCP_BASE_PATH": "/User/xxx/Desktop",
        "MINIMAX_RESOURCE_MODE": "url"
      }
    }
  }
}

Cursor

Go to Cursor → Preferences → Cursor Settings → MCP → Add new global MCP Server to add similar configuration.

⚠️ Important Notes:

• The API key must match the host address
• Global Host: https://api.minimaxi.chat (note the extra "i")
• Mainland China Host: https://api.minimax.chat

Available Tools

Text to Audio

Convert text to speech audio file.

Tool: text_to_audio
Parameters:
- text: Text to convert (required)
- model: Model version (default: speech-02-hd)
- voiceId: Voice ID (default: male-qn-qingse)
- speed: Speech speed (range: 0.5-2.0, default: 1.0)
- vol: Volume (range: 0.1-10.0, default: 1.0)
- pitch: Pitch (range: -12 to 12, default: 0)
- emotion: Emotion (options: happy, sad, angry, etc., default: happy)
- format: Audio format (default: mp3)

Play Audio

Play an audio file (WAV or MP3).

Tool: play_audio
Parameters:
- inputFilePath: Path to the audio file (required)
- isUrl: Whether the audio file is a URL (default: false)

Voice Clone

Clone a voice from an audio file.

Tool: voice_clone
Parameters:
- audioFile: Path to audio file (required)
- voiceId: Voice ID (required)
- text: Text for demo audio (optional)

Text to Image

Generate images based on text prompts.

Tool: text_to_image
Parameters:
- prompt: Image description (required)
- model: Model version (default: image-01)
- aspectRatio: Aspect ratio (default: 1:1)
- n: Number of images (range: 1-9, default: 1)
- subjectReference: Path to reference image (optional)

Generate Video

Generate videos based on text prompts.

Tool: generate_video
Parameters:
- prompt: Video description (required)
- model: Model version (default: T2V-01)
- firstFrameImage: Path to first frame image (optional)
- asyncMode: Whether to use async mode (default: false)

Query Video Generation Status

Query the status of an asynchronous video generation task.

Tool: query_video_generation
Parameters:
- taskId: The Task ID returned by generate_video (required)

Transport Modes

MiniMax MCP JS supports three communication modes:

• stdio (default): For local MCP client integration
• REST: For API services and cross-language calls
• SSE: For applications requiring server push

Using with Async Video Generation

When using generate_video with asyncMode: true, you'll need to follow up with query_video_generation to check the status and get the result. Consider defining completion rules in your MCP client to handle this automatically.

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.