MCP Server Aoai Dalle3

🚀 Azure OpenAI DALL-E 3 MCP Server

An implementation of an MCP (Model Context Protocol) server integrating Azure OpenAI DALL-E 3. This server serves as a bridge between the image generation capabilities of Azure OpenAI's DALL-E 3 and MCP clients.

🚀 Quick Start

Available Tools

generate_image

Generate an image using AOAI DALL-E 3 with the following parameters:

• prompt (Required): A text description of the image.
• size (Optional): The size of the image (Default: 1024x1024). Available options:
  • 1024x1024
  • 1792x1024
  • 1024x1792
• quality (Optional): The quality of the image (Default: High Definition). Available options:
  • Standard
  • High Definition
• style (Optional): The style of the image (Default: Natural). Available options:
  • Vibrant
  • Natural

download_image

Download the generated image to local storage:

• imageUrl (Required): The URL of the image to download.
• localPath (Required): The path of the local directory to save the image.
• fileName (Required): The name of the downloaded file.

Environment Variables

The following environment variables must be set to configure the server:

• AZURE_OPENAI_ENDPOINT: The endpoint URL of your Azure OpenAI resource. You can find it in the Azure portal, in the "Keys and Endpoints" section of your OpenAI resource.
• AZURE_OPENAI_API_KEY: The API key of your Azure OpenAI resource. This can also be found in the "Keys and Endpoints" section.
• AZURE_OPENAI_DEPLOYMENT_NAME (Optional, default is "dalle3"): The name of the DALL-E 3 deployment in your Azure OpenAI resource.
• OPENAI_API_VERSION (Optional, default is "2024-02-15-preview"): The API version to use. Make sure it matches the version supported by your Azure OpenAI resource.

Building the Server

1. Install dependencies:

npm install

2. Build the server:

npm run build

MCP Client Configuration

{
  "mcpServers": {
    "dalle3": {
      "command": "node",
      "args": [
        "path/to/mcp-server-aoai-dalle3/build/index.js"
      ],
      "env": {
        "AZURE_OPENAI_ENDPOINT": "<endpoint>",
        "AZURE_OPENAI_API_KEY": "<key>",
        "AZURE_OPENAI_DEPLOYMENT_NAME": "<deployment>"
      }
    }
  }
}