midjourney-proxy-mcp

MCP server for ImagineAPI - generate Midjourney images from Claude, Cursor, and other AI tools.

Features

• Generate Midjourney images via ImagineAPI
• Query image generation status and results
• List recent generations with filtering
• Access generation statistics via MCP resources

Installation

# Using uvx (recommended)
uvx midjourney-proxy-mcp

# Using pip
pip install midjourney-proxy-mcp

Configuration

Environment Variables

Get your API token from ImagineAPI.

Claude Desktop

Add to your claude_desktop_config.json:

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

{
  "mcpServers": {
    "midjourney": {
      "command": "uvx",
      "args": ["midjourney-proxy-mcp"],
      "env": {
        "IMAGINEAPI_URL": "https://your-imagineapi.com",
        "IMAGINEAPI_TOKEN": "your-api-token"
      }
    }
  }
}

Claude Code

claude mcp add midjourney --env IMAGINEAPI_TOKEN=your-api-token -- uvx midjourney-proxy-mcp

Or add manually to ~/.claude/settings.json:

{
  "mcpServers": {
    "midjourney": {
      "command": "uvx",
      "args": ["midjourney-proxy-mcp"],
      "env": {
        "IMAGINEAPI_TOKEN": "your-api-token"
      }
    }
  }
}

Alternatively, create a .env file in your working directory:

IMAGINEAPI_TOKEN=your-api-token

Cursor

Add to .cursor/mcp.json in your project:

{
  "mcpServers": {
    "midjourney": {
      "command": "uvx",
      "args": ["midjourney-proxy-mcp"],
      "env": {
        "IMAGINEAPI_URL": "https://your-imagineapi.com",
        "IMAGINEAPI_TOKEN": "your-api-token"
      }
    }
  }
}

Tools

Tool Examples

Generate an image:

midjourney_imagine(prompt="A futuristic city at sunset --ar 16:9 --v 7")

Check status:

midjourney_get_status(image_id="abc123")

List recent images:

midjourney_list_images(limit=10, status="completed")

Resources

Image Status Flow

1. pending - Request received, queued for processing
2. in-progress - Midjourney is generating (progress percentage available)
3. completed - Done, upscaled_urls contains 4 upscaled images
4. failed - Error occurred, check error field

Development

# Install dependencies
uv sync

# Run tests
uv run pytest

# Run tests with coverage
uv run pytest --cov=midjourney_proxy_mcp

# Type checking
uv run mypy src/

# Linting
uv run ruff check src/ tests/

# Format code
uv run ruff format src/ tests/

# Run server locally
uv run midjourney-proxy-mcp

Related

• ImagineAPI Documentation
• MCP Protocol
• FastMCP

License

MIT