Tongyi Wanx MCP Server

🚀 Tongyi Wanxiang MCP Server

This is a TypeScript-based Model Context Protocol (MCP) server that specifically provides the text-to-image and text-to-video capabilities of Alibaba Cloud's Tongyi Wanxiang. Through the MCP protocol, this server allows large language models (LLMs) to directly call Tongyi Wanxiang's image and video generation APIs.

✨ Features

• Text-to-Image Integration: Connects to Alibaba Cloud's Tongyi Wanxiang text-to-image API, supporting high-quality AI image generation.
• Text-to-Video Integration: Connects to Alibaba Cloud's Tongyi Wanxiang text-to-video API, supporting high-quality AI video generation.
• Asynchronous Task Processing: Supports long-running image and video generation tasks, and retrieves the final results through asynchronous polling.
• MCP Protocol Support: Complies with the Model Context Protocol specification and can seamlessly collaborate with LLMs that support MCP.

📦 Installation

Environment Requirements

• Node.js >= 16.x
• npm >= 8.x or pnpm

Installation Steps

1. Install Dependencies

   npm install
   

2. Build the Project

   npm run build
   

3. Start the Server

   npm start
   

💻 Usage Examples

Basic Usage

Take the Bailian platform as an example:

{
  "mcpServers": {
    "tongyi-wanxiang": {
      "command": "npx",
      "args": [
        "-y",
        "tongyi-wanx-mcp-server@latest"
      ],
      "env": {
        "DASHSCOPE_API_KEY": "<Your Tongyi Wanxiang API access key>"
      }
    }
  }
}

📚 Documentation

API Interface Descriptions

Text-to-Image Generation Interface

• Parameters:
  • prompt: Text description of the image.
  • width: Image width, default is 512.
  • height: Image height, default is 512.
  • negative_prompt (optional): Content to be reduced in the generated image.
• Return Value:

{
  "task_id": string // Unique identifier for the task
}

Text-to-Image Result Retrieval Interface

• Parameters:
  • task_id: Task ID returned during text-to-image generation.
• Return Value:

{
  "status": "completed" || "processing" || "failed",
  "result_url": string, // Image URL, only returned when completed
  "error_message": string // Error message, returned when failed
}

Text-to-Video Generation Interface

• Parameters:
  • prompt: Text description of the video.
  • width: Video width, default is 512.
  • height: Video height, default is 512.
  • duration (optional): Video duration, default is 10 seconds.
  • negative_prompt (optional): Content to be reduced in the generated video.
• Return Value:

{
  "task_id": string // Unique identifier for the task
}

Text-to-Video Result Retrieval Interface

• Parameters:
  • task_id: Task ID returned during text-to-video generation.
• Return Value:

{
  "status": "completed" || "processing" || "failed",
  "result_url": string, // Video URL, only returned when completed
  "error_message": string // Error message, returned when failed
}

Configuration File

// config.ts
export const CONFIG = {
  // Image generation related configuration
  IMAGE_GENERATION: {
    pollingInterval: 1000, // Polling interval time, default is 1 second
    maxRetries: 5,         // Maximum number of retries, default is 5 times
    timeout: 30000         // Task timeout time, default is 30 seconds
  },

  // Video generation related configuration
  VIDEO_GENERATION: {
    pollingInterval: 2000, // Polling interval time, default is 2 seconds
    maxRetries: 10,       // Maximum number of retries, default is 10 times
    timeout: 600000        // Task timeout time, default is 10 minutes
  }
};

⚠️ Important Note

1. API Permissions: Ensure that you have a valid Tongyi Wanxiang API access key and keep it safe.
2. Asynchronous Processing: Image generation may take several seconds to tens of seconds, and video generation takes even longer. Please be patient.
3. Polling Mechanism: The polling interval and number of retries on the server side should be reasonably set according to the specific scenario to avoid resource waste.
4. Error Handling: For failed tasks, check the error_message for more information and take corresponding measures.

📄 References

• Tongyi Wanxiang API Documentation
• Model Context Protocol (MCP) Specification