Azure AI Image Editor MCP Server

Azure Image Editor MCP Server

中文 | English

This is an MCP (Model Context Protocol) server that supports Azure AI Foundry image generation and editing capabilities.

Features

Text-to-Image Generation - Generate high-quality images from text descriptions using Azure AI Foundry models
Image Editing - Edit and modify existing images
Configurable Models - Support for multiple Azure AI models via environment variables

Demo

Click 👇 to go to the demo on YouTube

Project Structure

azure-image-editor/
├── .venv/                        # Python virtual environment
├── src/
│   ├── azure_image_client.py     # Azure API client
│   └── mcp_server.py             # STDIO MCP server
├── tests/                        # Test files
├── logs/                         # Server logs
├── tmp/                          # Temporary files
├── requirements.txt              # Python dependencies
├── .env                          # Environment configuration
├── .env.example                  # Environment configuration template
└── README.md                     # Project documentation

Prerequisites

⚠️ Important: Before using this MCP server, you must deploy the required model in your Azure AI Foundry environment.

Azure AI Foundry Model Deployment

Access Azure AI Foundry: Go to Azure AI Foundry
Deploy the model: Deploy flux.1-kontext-pro (or your preferred model) in your Azure AI Foundry workspace
Get deployment details: Note down your:
- Base URL (endpoint)
- API key
- Deployment name
- Model name

Without proper model deployment, the MCP server will not function correctly.

Installation and Setup

Clone and setup environment:

git clone https://github.com/satomic/Azure-AI-Image-Editor-MCP.git
cd azure-image-editor
python -m venv .venv
source .venv/bin/activate  # Linux/Mac
# or .venv\Scripts\activate  # Windows
pip install -r requirements.txt

Configure VSCode MCP

Add the following to your VSCode MCP configuration:

{
  "servers": {
    "azure-image-editor": {
      "command": "/full/path/to/.venv/bin/python",
      "args": ["/full/path/to/azure-image-editor/src/mcp_server.py"],
      "env": {
        "AZURE_BASE_URL": "https://your-endpoint.services.ai.azure.com", // deployment endpoint
        "AZURE_API_KEY": "${input:azure-api-key}",
        "AZURE_DEPLOYMENT_NAME": "FLUX.1-Kontext-pro", // The name you gave your deployment
        "AZURE_MODEL": "flux.1-kontext-pro", // Default model
        "AZURE_API_VERSION": "2025-04-01-preview" // Default API version
      }
    }
  },
  "inputs": [
    {
      "id": "azure-api-key",
      "type": "promptString",
      "description": "Enter your Azure API Key",
      "password": "true"
    }
  ]
}

Important: Replace /full/path/to/ with the actual absolute path to this project directory.

Available MCP Tools

1. generate_image

Generate images from text prompts

Parameters:

prompt (required): English text description for image generation
size (optional): Image size - "1024x1024", "1792x1024", "1024x1792", default: "1024x1024"
output_path (optional): Output file path, returns base64 encoded image if not provided

Example:

{
  "name": "generate_image",
  "arguments": {
    "prompt": "A beautiful sunset over mountains",
    "size": "1024x1024",
    "output_path": "/path/to/output/image.png"
  }
}

2. edit_image

Edit existing images with intelligent dimension preservation

Parameters:

image_path (required): Path to the image file to edit
prompt (required): English text description of how to edit the image
size (optional): Output image size, uses original dimensions if not specified
output_path (optional): Output file path, returns base64 encoded image if not provided

Example:

{
  "name": "edit_image",
  "arguments": {
    "image_path": "/path/to/input/image.png",
    "prompt": "Make this black and white",
    "output_path": "/path/to/output/edited_image.png"
  }
}

Technical Specifications

Python version: 3.8+
Main dependencies:
- mcp: MCP protocol support
- httpx: HTTP client with timeout handling
- pillow: Image processing and dimension detection
- aiofiles: Async file operations
- pydantic: Data validation
- python-dotenv: Environment variable management
Azure AI Foundry:
- Default model: flux.1-kontext-pro (configurable)
- Default API version: 2025-04-01-preview (configurable)
- Supported image sizes: 1024x1024, 1792x1024, 1024x1792
- Timeout: 5 minutes per request

Troubleshooting

Timeout Errors: Image processing has 5-minute timeout, check network connectivity
API Errors: Verify Azure credentials and endpoint URL
Dependency Issues: Ensure virtual environment is activated and dependencies installed
Server Connection Issues: Verify VSCode MCP configuration path is correct

License

MIT License

This server cannot be installed

security - not tested

license - not found

quality - not tested

How are these scores calculated?

remote-capable server

The server can be hosted and run remotely because it primarily relies on remote services or has no dependency on the local environment.

Enables text-to-image generation and image editing using Azure AI Foundry models. Supports generating high-quality images from text descriptions and modifying existing images through natural language prompts.

Related MCP Servers

MCP Flux Studio
jmanhype
A
security
A
license
A
quality
A server that integrates Flux's advanced image generation and manipulation features into AI coding assistants, enabling seamless text-to-image and image control workflows in IDEs like Cursor and Windsurf.
Last updated -
4
20
MIT License
Image Toolkit MCP Server
Kira-Pgr
-
security
A
license
-
quality
A server that provides AI-powered image generation, modification, and processing capabilities through the Model Context Protocol, leveraging Google Gemini models and other image services.
Last updated -
13
MIT License
OpenAI Image Generation MCP Server
IncomeStreamSurfer
-
security
A
license
-
quality
Provides tools for generating and editing images using OpenAI's gpt-image-1 model via an MCP interface, enabling AI assistants to create and modify images based on text prompts.
Last updated -
16
Apache 2.0
GPT Image 1 MCP
CLOUDWERX-DEV
A
security
A
license
A
quality
A Model Context Protocol server that enables generating and editing images using OpenAI's gpt-image-1 model, allowing AI assistants to create and modify images from text prompts.
Last updated -
2
36
16
MIT License

View all related MCP servers