# Midjourney

Wires Midjourney into an AI agent through the AceDataCloud API: text-to-image, variations, edits, video. Useful when you need visuals without leaving the chat.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 15
- Author: AceDataCloud
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/AceDataCloud/MidjourneyMCP
- Updated: 2026-10-18
- HTML: https://affpapa.org/en/nevibecode/mcp/midjourney

## What it does

The server exposes Midjourney as a set of tools. `midjourney_imagine` turns a prompt into an image, `midjourney_transform` handles upscaling, variations and panning, `midjourney_blend` fuses several pictures. Reference-based generation, masked editing and reverse-prompt description are there too. Two more tools build a clip from text and extend an existing video.

Everything goes through AceDataCloud rather than Midjourney directly. You pick one of three routes: hosted OAuth at `https://midjourney.mcp.acedata.cloud/mcp`, the same URL with a token in the `Authorization: Bearer …` header, or a local stdio process started with `uvx mcp-midjourney`. The last two need an AceDataCloud account and an API token. Even the local variant still calls their API, so it does not work offline.

OAuth depends on the client supporting remote MCP servers; the stdio path wants Python 3.10+ and `uvx`. Do not configure a login and a fixed `Authorization` header for the same server at once. Hosted usage is metered per operation.

## Requirements
- Needs: Python and uv (commands run via uvx)
- Remote server: `https://midjourney.mcp.acedata.cloud/mcp`
- Environment variables: `ACEDATACLOUD_API_TOKEN` — keys and tokens: ask the human for the values, never commit them or put them in shared files.

## Install

### Claude Code (native platform)

1. **Platform CLI: remote server**
```bash
claude mcp add --transport http mcp-midjourney https://midjourney.mcp.acedata.cloud/mcp
```

2. **Platform CLI**
```bash
claude mcp add --env ACEDATACLOUD_API_TOKEN=<ACEDATACLOUD_API_TOKEN> --transport stdio midjourney -- uvx mcp-midjourney
```
Replace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from mcp-midjourney <command>

### Codex

1. **Platform CLI: remote server**
```bash
codex mcp add midjourney --url https://midjourney.mcp.acedata.cloud/mcp
```

2. **Platform CLI**
```bash
codex mcp add midjourney --env ACEDATACLOUD_API_TOKEN=<ACEDATACLOUD_API_TOKEN> -- uvx mcp-midjourney
```
Replace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from mcp-midjourney <command>

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "midjourney": {
            "url": "https://midjourney.mcp.acedata.cloud/mcp"
        }
    }
}
```
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "midjourney": {
            "command": "uvx",
            "args": [
                "mcp-midjourney"
            ],
            "env": {
                "ACEDATACLOUD_API_TOKEN": "<ACEDATACLOUD_API_TOKEN>"
            }
        }
    }
}
```
Replace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from mcp-midjourney <command>

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "midjourney": {
            "type": "http",
            "url": "https://midjourney.mcp.acedata.cloud/mcp"
        }
    }
}
```
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "midjourney": {
            "type": "stdio",
            "command": "uvx",
            "args": [
                "mcp-midjourney"
            ],
            "env": {
                "ACEDATACLOUD_API_TOKEN": "<ACEDATACLOUD_API_TOKEN>"
            }
        }
    }
}
```
Replace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from mcp-midjourney <command>

### Gemini CLI

1. **Platform CLI: remote server**
```bash
gemini mcp add -t http midjourney https://midjourney.mcp.acedata.cloud/mcp
```

2. **Platform CLI**
```bash
gemini mcp add -e ACEDATACLOUD_API_TOKEN=<ACEDATACLOUD_API_TOKEN> midjourney uvx mcp-midjourney
```
Replace <…> with your own values. uvx runs the command named after the package; if the README names another one, use uvx --from mcp-midjourney <command>

## When to use it
- generate an image from a text prompt inside the chat
- upscale or vary an existing picture
- produce a clip from a prompt and a reference image
- edit an image with a mask and a description
- recover a reverse prompt from a finished image

## Example prompts
- Draw a cover image for a coffee article with midjourney_imagine
- Upscale this image and show me the variations
- Generate a short video from this prompt and reference image

## Similar
- [MCP Toolbox for Databases](https://affpapa.org/en/nevibecode/mcp/googleapis-mcp-toolbox-for-databases.md) — MCP server · ★ 16717
- [labelhead-artist-momentum](https://affpapa.org/en/nevibecode/mcp/labelhead-artist-momentum.md) — MCP server · ★ 107423
- [Agent Skills Search Server](https://affpapa.org/en/nevibecode/mcp/agent-skills-search-server.md) — MCP server · ★ 26559
- [Skyvern](https://affpapa.org/en/nevibecode/mcp/skyvern.md) — MCP server · ★ 23263
- [Nhost](https://affpapa.org/en/nevibecode/mcp/nhost.md) — MCP server · ★ 9366
- [PraisonAI](https://affpapa.org/en/nevibecode/mcp/praisonai.md) — MCP server · ★ 9289

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md