io.github.AceDataCloud/mcp-midjourney

Official

by AceDataCloud · Python

Midjourney

MCP server for Midjourney AI image generation and editing

Generate and edit images using Midjourney AI.

Topics

ai-imageimage-generationmcp-servermodel-context-protocoldeveloper-toolsmidjourney-api

README.md17 KBView on GitHub

MidjourneyMCP

A Model Context Protocol (MCP) server for AI image and video generation using Midjourney through the AceDataCloud API.

Generate AI images, videos, and manage creative projects directly from Claude, VS Code, or any MCP-compatible client.

Features

Image Generation - Create AI-generated images from text prompts
Image Transformation - Upscale, create variations, zoom, and pan images
Image Blending - Combine multiple images into creative fusions
Reference-Based Generation - Use existing images as inspiration
Image Description - Get AI descriptions of images (reverse prompt)
Image Editing - Edit images with text prompts and masks
Video Generation - Create videos from text and reference images
Video Extension - Extend existing videos to make them longer
Translation - Translate Chinese prompts to English
Task Tracking - Monitor generation progress and retrieve results

Tool Reference

Tool	Description
`midjourney_imagine`	Generate AI images from a text prompt using Midjourney.
`midjourney_transform`	Transform an existing Midjourney image with various operations.
`midjourney_blend`	Blend multiple images together using Midjourney.
`midjourney_with_reference`	Generate images using a reference image as inspiration.
`midjourney_edit`	Edit an existing image using Midjourney.
`midjourney_describe`	Get AI-generated descriptions of an image.
`midjourney_generate_video`	Generate a video from text prompt and reference image using Midjourney.
`midjourney_extend_video`	Extend an existing Midjourney video to make it longer.
`midjourney_translate`	Translate Chinese text to English for use as Midjourney prompts.
`midjourney_shorten`	Analyze and shorten long Midjourney prompts while preserving key ideas.
`midjourney_get_seed`	Get the seed value of a previously generated Midjourney image.
`midjourney_get_task`	Query the status and result of a Midjourney generation task.
`midjourney_get_tasks_batch`	Query multiple Midjourney generation tasks at once.
`midjourney_list_actions`	List all available Midjourney API actions and corresponding tools.
`midjourney_get_prompt_guide`	Get guidance on writing effective prompts for Midjourney.
`midjourney_list_transform_actions`	List all available transformation actions for Midjourney images.

Quick Start

1. Get Your API Token

Sign up at AceDataCloud Platform
Go to the API documentation page
Click "Acquire" to get your API token
Copy the token for use below

2. Use the Hosted Server (Recommended)

AceDataCloud hosts a managed MCP server — no local installation required.

Endpoint: https://midjourney.mcp.acedata.cloud/mcp

All requests require a Bearer token. Use the API token from Step 1.

Claude.ai

Connect directly on Claude.ai with OAuth — no API token needed:

Go to Claude.ai Settings → Integrations → Add More
Enter the server URL: https://midjourney.mcp.acedata.cloud/mcp
Complete the OAuth login flow
Start using the tools in your conversation

Claude Desktop

Add to your config (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):

json

{
  "mcpServers": {
    "midjourney": {
      "type": "streamable-http",
      "url": "https://midjourney.mcp.acedata.cloud/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_TOKEN"
      }
    }
  }
}

Cursor / Windsurf

Add to your MCP config (.cursor/mcp.json or .windsurf/mcp.json):

json

{
  "mcpServers": {
    "midjourney": {
      "type": "streamable-http",
      "url": "https://midjourney.mcp.acedata.cloud/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_TOKEN"
      }
    }
  }
}

VS Code (Copilot)

Add to your VS Code MCP config (.vscode/mcp.json):

json

{
  "servers": {
    "midjourney": {
      "type": "streamable-http",
      "url": "https://midjourney.mcp.acedata.cloud/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_TOKEN"
      }
    }
  }
}

Or install the Ace Data Cloud MCP extension for VS Code, which registers the hosted MCP servers with one-click setup.

JetBrains IDEs

Go to Settings → Tools → AI Assistant → Model Context Protocol (MCP)
Click Add → HTTP
Paste:

json

{
  "mcpServers": {
    "midjourney": {
      "url": "https://midjourney.mcp.acedata.cloud/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_TOKEN"
      }
    }
  }
}

Claude Code

Claude Code supports MCP servers natively:

bash

claude mcp add midjourney --transport http https://midjourney.mcp.acedata.cloud/mcp \
  -h "Authorization: Bearer YOUR_API_TOKEN"

Or add to your project's .mcp.json:

json

{
  "mcpServers": {
    "midjourney": {
      "type": "streamable-http",
      "url": "https://midjourney.mcp.acedata.cloud/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_TOKEN"
      }
    }
  }
}

Cline

Add to Cline's MCP settings (.cline/mcp_settings.json):

json

{
  "mcpServers": {
    "midjourney": {
      "type": "streamable-http",
      "url": "https://midjourney.mcp.acedata.cloud/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_TOKEN"
      }
    }
  }
}

Amazon Q Developer

Add to your MCP configuration:

json

{
  "mcpServers": {
    "midjourney": {
      "type": "streamable-http",
      "url": "https://midjourney.mcp.acedata.cloud/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_TOKEN"
      }
    }
  }
}

Roo Code

Add to Roo Code MCP settings:

json

{
  "mcpServers": {
    "midjourney": {
      "type": "streamable-http",
      "url": "https://midjourney.mcp.acedata.cloud/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_TOKEN"
      }
    }
  }
}

Continue.dev

Add to .continue/config.yaml:

yaml

mcpServers:
  - name: midjourney
    type: streamable-http
    url: https://midjourney.mcp.acedata.cloud/mcp
    headers:
      Authorization: "Bearer YOUR_API_TOKEN"

Zed

Add to Zed's settings (~/.config/zed/settings.json):

json

{
  "language_models": {
    "mcp_servers": {
      "midjourney": {
        "url": "https://midjourney.mcp.acedata.cloud/mcp",
        "headers": {
          "Authorization": "Bearer YOUR_API_TOKEN"
        }
      }
    }
  }
}

cURL Test

bash

# Health check (no auth required)
curl https://midjourney.mcp.acedata.cloud/health

# MCP initialize
curl -X POST https://midjourney.mcp.acedata.cloud/mcp \
  -H "Content-Type: application/json" \
  -H "Accept: application/json" \
  -H "Authorization: Bearer YOUR_API_TOKEN" \
  -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-03-26","capabilities":{},"clientInfo":{"name":"test","version":"1.0"}}}'

3. Or Run Locally (Alternative)

If you prefer to run the server on your own machine:

bash

# Install from PyPI
pip install mcp-midjourney
# or
uvx mcp-midjourney

# Set your API token
export ACEDATACLOUD_API_TOKEN="your_token_here"

# Run (stdio mode for Claude Desktop / local clients)
mcp-midjourney

# Run (HTTP mode for remote access)
mcp-midjourney --transport http --port 8000

Claude Desktop (Local)

json

{
  "mcpServers": {
    "midjourney": {
      "command": "uvx",
      "args": ["mcp-midjourney"],
      "env": {
        "ACEDATACLOUD_API_TOKEN": "your_token_here"
      }
    }
  }
}

Docker (Self-Hosting)

bash

docker pull ghcr.io/acedatacloud/mcp-midjourney:latest
docker run -p 8000:8000 ghcr.io/acedatacloud/mcp-midjourney:latest

Clients connect with their own Bearer token — the server extracts the token from each request's Authorization header.

Available Tools

Image Generation

Tool	Description
`midjourney_imagine`	Generate images from a text prompt (creates 2x2 grid)
`midjourney_transform`	Transform images (upscale, variation, zoom, pan)
`midjourney_blend`	Blend multiple images together
`midjourney_with_reference`	Generate using a reference image as inspiration

Image Editing

Tool	Description
`midjourney_edit`	Edit an existing image with text prompt
`midjourney_describe`	Get AI descriptions of an image (reverse prompt)

Video

Tool	Description
`midjourney_generate_video`	Generate video from text and reference image
`midjourney_extend_video`	Extend existing video to make it longer

Utility

Tool	Description
`midjourney_translate`	Translate Chinese text to English for prompts
`midjourney_get_seed`	Get the seed value of a generated image

Tasks

Tool	Description
`midjourney_get_task`	Query a single task status
`midjourney_get_tasks_batch`	Query multiple tasks at once

Information

Tool	Description
`midjourney_list_actions`	List available API actions
`midjourney_get_prompt_guide`	Get prompt writing guide
`midjourney_list_transform_actions`	List transformation actions

Usage Examples

Generate Image from Prompt

code

User: Create a cyberpunk city at night

Claude: I'll generate a cyberpunk city image for you.
[Calls midjourney_imagine with prompt="Cyberpunk city at night, neon lights, rain, futuristic, detailed --ar 16:9"]

Upscale an Image

code

User: Upscale the second image

Claude: I'll upscale the top-right image from the grid.
[Calls midjourney_transform with image_id and action="upscale2"]

Blend Multiple Images

code

User: Blend these two images: [url1] and [url2]

Claude: I'll blend these images together.
[Calls midjourney_blend with image_urls=[url1, url2]]

Generate Video

code

User: Animate this image [url] with gentle movement

Claude: I'll create a video from this image.
[Calls midjourney_generate_video with image_url and prompt="Gentle camera movement, cinematic"]

Generation Modes

Mode	Description
`fast`	Recommended for most use cases (default)
`turbo`	Faster generation, uses more credits
`relax`	Slower generation, cheaper

Configuration

Environment Variables

Variable	Description	Default
`ACEDATACLOUD_API_TOKEN`	API token from AceDataCloud	Required
`ACEDATACLOUD_API_BASE_URL`	API base URL	`https://api.acedata.cloud`
`ACEDATACLOUD_OAUTH_CLIENT_ID`	OAuth client ID (hosted mode)	—
`ACEDATACLOUD_PLATFORM_BASE_URL`	Platform base URL	`https://platform.acedata.cloud`
`MIDJOURNEY_DEFAULT_MODE`	Default generation mode	`fast`
`MIDJOURNEY_REQUEST_TIMEOUT`	Request timeout in seconds	`1800`
`LOG_LEVEL`	Logging level	`INFO`

Command Line Options

bash

mcp-midjourney --help

Options:
  --version          Show version
  --transport        Transport mode: stdio (default) or http
  --port             Port for HTTP transport (default: 8000)

Development

Setup Development Environment

bash

# Clone repository
git clone https://github.com/AceDataCloud/MidjourneyMCP.git
cd MidjourneyMCP

# Create virtual environment
python -m venv .venv
source .venv/bin/activate  # or `.venv\Scripts\activate` on Windows

# Install with dev dependencies
pip install -e ".[dev,test]"

Run Tests

bash

# Run unit tests
pytest

# Run with coverage
pytest --cov=core --cov=tools

# Run integration tests (requires API token)
pytest tests/test_integration.py -m integration

Code Quality

bash

# Format code
ruff format .

# Lint code
ruff check .

# Type check
mypy core tools

Build & Publish

bash

# Install build dependencies
pip install -e ".[release]"

# Build package
python -m build

# Upload to PyPI
twine upload dist/*

Project Structure

code

MidjourneyMCP/
├── core/                   # Core modules
│   ├── __init__.py
│   ├── client.py          # HTTP client for Midjourney API
│   ├── config.py          # Configuration management
│   ├── exceptions.py      # Custom exceptions
│   ├── server.py          # MCP server initialization
│   ├── types.py           # Type definitions
│   └── utils.py           # Utility functions
├── tools/                  # MCP tool definitions
│   ├── __init__.py
│   ├── describe_tools.py  # Image description tools
│   ├── edits_tools.py     # Image editing tools
│   ├── imagine_tools.py   # Image generation tools
│   ├── info_tools.py      # Information tools
│   ├── task_tools.py      # Task query tools
│   ├── translate_tools.py # Translation tools
│   └── video_tools.py     # Video generation tools
├── prompts/                # MCP prompt templates
│   └── __init__.py
├── tests/                  # Test suite
├── deploy/                 # Deployment configs
│   └── production/
│       ├── deployment.yaml
│       ├── ingress.yaml
│       └── service.yaml
├── .env.example           # Environment template
├── .gitignore
├── CHANGELOG.md
├── Dockerfile             # Docker image for HTTP mode
├── docker-compose.yaml    # Docker Compose config
├── LICENSE
├── main.py                # Entry point
├── pyproject.toml         # Project configuration
└── README.md

API Reference

This server wraps the AceDataCloud Midjourney API:

Midjourney Imagine API - Image generation
Midjourney Describe API - Image description
Midjourney Tasks API - Task queries
Midjourney Edits API - Image editing
Midjourney Videos API - Video generation
Midjourney Translate API - Translation

Contributing

Contributions are welcome! Please:

Fork the repository
Create a feature branch (git checkout -b feature/amazing)
Commit your changes (git commit -m 'Add amazing feature')
Push to the branch (git push origin feature/amazing)
Open a Pull Request

License

MIT License - see LICENSE for details.

Links

Made with love by AceDataCloud

Install

Configuration

Environment variables

ACEDATACLOUD_API_TOKENrequiredsecret

API token from Ace Data Cloud (https://platform.acedata.cloud)

claude_desktop_config.json

{
  "mcpServers": {
    "mcp-midjourney": {
      "command": "uvx",
      "args": [
        "mcp-midjourney"
      ],
      "env": {
        "ACEDATACLOUD_API_TOKEN": "<YOUR_ACEDATACLOUD_API_TOKEN>"
      }
    }
  }
}