Using MoArk's Model API via MCP

MoArk MCP Service is a Model Context Protocol (MCP) endpoint that exposes MoArk models to MCP-compatible clients. It provides powerful multimedia generation capabilities, including text-to-image and text-to-speech functions, enabling AI assistants to create rich visual and audio content.

Quick Start

1. Visit https://moark.ai/dashboard/settings/tokens to get your Access Token.

2. Configure the MCP service in your client (e.g., Cursor).
   

Features

• Text-to-Image: Supports multiple image generation models, capable of creating high-quality images from text descriptions
• Text-to-Speech: Converts text to natural speech with support for multiple audio formats
• Configurable API base URL, supporting different MoArk instances
• Supports multiple response formats (Base64, URL, binary stream, etc.)
• Flexible parameter configuration to meet various usage scenarios

Practical Scenarios: Multimedia Content Creation

1. Generate illustrations based on text descriptions
   
2. Create voice narration for documents or presentations
   
3. Batch generate marketing materials
   

MCP Hosts Configuration

Get Started

Configuring MoArk MCP Service requires a valid Access Token for authentication.

config.json

{
  "mcpServers": {
    "gitee-ai": {
      "url": "https://moark.ai/mcp/sse",
      "headers": {
        "Authorization": "Bearer <your_access_token>"
      }
    }
  }
}

Claude Desktop Configuration Example

1. Open the Claude Desktop configuration file:

   • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
   • Windows: %APPDATA%\Claude\claude_desktop_config.json

2. Add the MCP server configuration:

claude_desktop_config.json

{
  "mcpServers": {
    "gitee-ai": {
      "url": "https://moark.ai/mcp/sse",
      "headers": {
        "Authorization": "Bearer <YOUR_ACCESS_TOKEN>"
      }
    }
  }
}

3. Restart Claude Desktop

Cursor Configuration Example

1. Open the Cursor settings page, navigate to the "MCP Servers" configuration item.

2. Add the MCP server configuration, in the following format:

cursor-mcp-config.json

{
  "mcpServers": {
    "gitee-ai": {
      "url": "https://moark.ai/mcp/sse",
      "headers": {
        "Authorization": "Bearer <YOUR_ACCESS_TOKEN>"
      }
    }
  }
}

3. After saving the configuration, enable the corresponding MCP service and start using it

Available Tools

The server provides the following multimedia generation tools:

Image Generation Tools

Tool Name	Endpoint	Description
text_to_image	/images/generations	Generate images based on text descriptions

Features:

• Supports multiple image generation models (e.g., stable-diffusion-3.5-large-turbo)
• Configurable image size (e.g., 1024x1024)
• Supports reference images (base64 or URL)
• Multiple response formats: Base64 encoded or URL links
• Supports user identifier tracking

Request Parameters:

• model (required): Model name
• prompt (required): Text description
• size: Image size (e.g., 1024x1024)
• image: Reference image (base64 or URL)
• response_format: Response format (b64_json or url)

Parameter Notes

• Model names support namespaces, for example stable-diffusion-3.5-large-turbo or stabilityai/stable-diffusion-3.5-large-turbo.
• The n parameter currently supports only the value 1, so one image is generated per request.

Text-to-Speech Tools

Tool Name	Endpoint	Description
text_to_speech	/audio/speech	Convert text to speech

Features:

• Supports multiple speech synthesis models (e.g., whisper-large-v3-turbo)
• Multiple audio formats output (wav, mp3)
• Flexible response options: binary stream or URL link
• Generated audio URL expires after 1 hour

Request Parameters:

• model (required): Model name
• input (required): Input text
• response_format: Response format (url or blob, default is blob)

Audio File Reminder

When response_format: "url" is selected, the generated audio file download link expires after 1 hour. Please download and save it promptly.

Integration Instructions

MoArk MCP Service can be easily integrated into various AI assistants and applications that support the MCP protocol, enabling users to leverage powerful multimedia content generation capabilities. With these tools, AI assistants can:

• Quickly generate visual content based on user ideas
• Convert text content into audio, providing richer interaction experiences
• Support various application scenarios such as content creation, education, marketing promotion, etc.