Midjourney MCP Server
# Midjourney MCP server for Claude and ChatGPT
**Yes, ChatGPT, Claude and other AI agents can work in your Midjourney account.** Use Cotlet.dev to run prompts, create variations, upscale and animate images, search creations and organize folders without an API key.
## What you can ask
> Create a cinematic product image of a red bicycle at sunrise.
> Make three subtle variations of my latest creation.
> Upscale the strongest image from today and give me a download link.
> Animate this image into a five second video and extend it by four seconds.
> List my folders and move yesterday’s portrait creations into the right one.
## Connect in 2 minutes
Get your API key at https://cotlet.dev/app and export it as `COTLET_API_KEY`.
### Claude Code
```bash
claude mcp add --transport http cotlet https://cotlet.dev/mcp/v1 --header "Authorization: Bearer $COTLET_API_KEY"
```
### ChatGPT
Settings → Apps → add connector URL `https://cotlet.dev/mcp/v1`, then sign in with Cotlet.dev. No API key needed.
### Cursor
Copy `.cursor/mcp.json` from this repo into your project:
```json
{
"mcpServers": {
"cotlet": {
"url": "https://cotlet.dev/mcp/v1",
"headers": {
"Authorization": "Bearer ${COTLET_API_KEY}"
}
}
}
}
```
## Run it locally (stdio)
This repo is a real MCP server. It speaks MCP over stdio, lists its Midjourney tools without any key, and forwards every tool call to the hosted Cotlet.dev server. The hosted URL above stays the recommended way. Use this when your client only starts local servers.
```json
{"mcpServers":{"midjourney":{"command":"uvx","args":["midjourney-mcp"],"env":{"COTLET_API_KEY":"your-key"}}}}
```
Or with Docker:
```bash
docker build -t midjourney-mcp .
docker run -i --rm -e COTLET_API_KEY midjourney-mcp
```
Tools: `midjourney_guide`, `midjourney_status`, `midjourney_open`, `midjourney_read`, `midjourney_click`, `midjourney_type`, `midjourney_close`. Without `COTLET_API_KEY` a tool call answers: "Set COTLET_API_KEY. Get a key at https://cotlet.dev/app".
## Command line
Python 3.10+, nothing else to install. From PyPI:
```bash
pip install midjourney-mcp # or run it once: uvx midjourney-mcp connect
midjourney-mcp connect
```
Or straight from this repo:
```bash
export COTLET_API_KEY="your-key"
python3 midjourney_agent.py connect # ready config for Claude Code, Cursor, ChatGPT
python3 midjourney_agent.py status # is Midjourney ready in your Cotlet.dev account
python3 midjourney_agent.py guide # Midjourney screens and sign-in link
python3 midjourney_agent.py read # open Midjourney, read the page, close the browser
python3 midjourney_agent.py tools # list Cotlet.dev tools
python3 midjourney_agent.py serve # start the stdio MCP server (same as no argument)
```
## Questions from Midjourney users
**How do I connect Midjourney to ChatGPT or Claude?**
Sign up at cotlet.dev, log in to Midjourney once in its Cloud Browser and add Cotlet to ChatGPT or Claude, following the steps in your console. No API key is needed. ChatGPT and Claude then work in your Midjourney account through Cotlet, in their phone apps too.
**What can ChatGPT do in Midjourney?**
With Cotlet, ChatGPT, Claude and other AI agents handle jobs like these in Midjourney: run a list of prompts; sort new creations into folders; turn your best images into videos. You ask in plain words, and anything that reaches other people waits for your OK first.
**Can I use the Midjourney API without an AI agent?**
Yes. Call Cotlet's REST API from a script or an HTTP step in n8n, Make or Zapier with your Cotlet key. MCP is the alternative for AI agents; you do not need to connect an agent to use REST.
**How do I get access?**
Create a free account at https://cotlet.dev, open Midjourney under Integrations in the console and log in to Midjourney in its Cloud Browser. The trial starts when you sign up, no card asked.
## Find it on
- [Midjourney on Cotlet.dev](https://cotlet.dev/integrations/midjourney-api-mcp-server)
- [All Cotlet packages](https://github.com/cotlet-connect)
---
More: https://cotlet.dev/integrations/midjourney-api-mcp-server?utm_source=github&utm_medium=readme&utm_campaign=midjourney
Request access: https://cotlet.dev/signup?app=midjourney&utm_source=github&utm_medium=readme&utm_campaign=midjourney
TDQS
Scored across 7 tools
Each tool has a clearly distinct role: guide, status, browser lifecycle, page reading, and element interaction. Open/read/click/type are standard browser primitives with clear boundaries and no overlap.
All tools use a consistent midjourney_ prefix followed by a simple action verb. The pattern is predictable and easy to scan.
Seven tools is well-scoped for a browser-automation wrapper around Midjourney. Setup, session management, and page interaction each have an appropriate dedicated tool.
The core browser session and interaction loop is covered, but important Midjourney workflows are missing: no screenshot or visual inspection for generated images, no wait/poll tool for long generations, no upload for reference images, and no scroll/navigation helpers. Agents can work around some gaps with repeated reads, but not all.