Midjourney MCP Integration Guide

midjourney MCP 服务器集成

MCP (Model Context Protocol) is a model context protocol launched by Anthropic that allows AI models (such as Claude, GPT, etc.) to call external tools through standardized interfaces. With the Midjourney MCP Server provided by AceData Cloud, you can directly generate and edit AI images in AI clients like Claude Desktop, VS Code, Cursor, etc.

Feature Overview

The Midjourney MCP Server provides the following core functionalities:

• Image Generation (Imagine) — Generate high-quality images from text prompts
• Image Editing — Make local modifications to generated images
• Image Transformation — Zoom in, zoom out, and pan existing images
• Image Blending (Blend) — Merge multiple images into a new image
• Reference Image Generation — Guide generation using reference images
• Image Description (Describe) — Generate text descriptions based on images
• Prompt Translation — Translate Chinese prompts into English
• Seed Retrieval — Obtain the seed value of an image for reproduction
• Video Generation — Generate dynamic videos based on images
• Task Query — Monitor generation progress and obtain results

Prerequisites

Before use, you need to obtain an AceData Cloud API Token:

1. Register or log in to the AceData Cloud platform
2. Go to the Midjourney Imagine API page
3. Click “Acquire” to get the API Token (first-time applicants receive free credits)

Installation Configuration

Method 1: pip Installation (Recommended)

pip install mcp-midjourney

Method 2: Source Installation

git clone https://github.com/AceDataCloud/MCPMidjourney.git
cd MCPMidjourney
pip install -e .

Once installed, you can use the mcp-midjourney command to start the service.

Using in Claude Desktop

Edit the Claude Desktop configuration file:

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

Add the following configuration:

{
  "mcpServers": {
    "midjourney": {
      "command": "mcp-midjourney",
      "env": {
        "ACEDATACLOUD_API_TOKEN": "Your API Token"
      }
    }
  }
}

If using uvx (no need to install packages in advance):

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

After saving the configuration, restart Claude Desktop to use Midjourney-related tools in the conversation.

Using in VS Code / Cursor

Create a .vscode/mcp.json in the project root directory:

{
  "servers": {
    "midjourney": {
      "command": "mcp-midjourney",
      "env": {
        "ACEDATACLOUD_API_TOKEN": "Your API Token"
      }
    }
  }
}

Or use uvx:

{
  "servers": {
    "midjourney": {
      "command": "uvx",
      "args": ["mcp-midjourney"],
      "env": {
        "ACEDATACLOUD_API_TOKEN": "Your API Token"
      }
    }
  }
}

Available Tools List

Tool Name	Description
midjourney_imagine	Generate images from text prompts
midjourney_edit	Edit local areas of existing images
midjourney_transform	Zoom in, zoom out, and pan existing images
midjourney_blend	Merge multiple images into one
midjourney_with_reference	Generate images using reference images
midjourney_describe	Generate text descriptions based on images
midjourney_translate	Translate prompts into English
midjourney_get_seed	Retrieve the seed value of an image
midjourney_generate_video	Generate videos based on images
midjourney_extend_video	Extend existing videos
midjourney_get_task	Query the status of a single task
midjourney_get_tasks_batch	Batch query task statuses

Usage Examples

After configuration, you can directly call these functions in the AI client using natural language, for example:

• “Help me generate a cyberpunk-style city night scene”
• “Change the background of this image to the seaside”
• “Blend these four images into one”
• “Describe the content of this image”
• “Make a video from this image”
• “Zoom in on the second variant of this image”

More Information

• GitHub Repository: AceDataCloud/MCPMidjourney
• PyPI Package: mcp-midjourney
• API Documentation: Midjourney Generation API