Use Midjourney with your AI.
Connect your account once and let the AI you already use work with it, without building another integration. Generate professional AI art via Midjourney. use 'imagine' for text-to-image, upscale grids, and perform camera edits.
Developed, maintained, and hosted by Vinkius.
MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED
Waiting for input…
Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.
Complete set · 10 capabilities
The complete Midjourney capability set.
These are the exact actions your AI can choose when you ask it to work with Midjourney.
01-04
4 capabilities in this set.
Part of 10 available through Midjourney.
- 01
Reroll job
Re-run identical prompt arguments dropping new sets of outputs
- 02
Blend images
Pass absolute valid URLs delimited strictly by commas. Blend 2-5 explicit images into a new unique composition
- 03
Describe image
Reverse engineer text descriptions from an input image via Midjourney
- 04
Generate image
Always retrieve the returning Job ID to poll get_job tracking its process till completion. Generate images from a text prompt using Midjourney generative models
05-07
3 capabilities in this set.
Part of 10 available through Midjourney.
- 05
Generate variation
Returns a new Job. Create variant branches from a specific Midjourney grid image
- 06
Get job
DO NOT loop aggressively, sleep in between. Get the active execution status of an ongoing Midjourney job
- 07
Zoom out image
Widen the perspective zooming out explicitly
08-10
3 capabilities in this set.
Part of 10 available through Midjourney.
- 08
List jobs
List recent history representing previously executed Midjourney prompts
- 09
Pan image
Extrapolate frame borders panning natively over a direction
- 10
Upscale image
Polled async. Extract and upscale a single specific tile off a 2x2 grid
Observed, not estimated
852ms average. Fast in production.
Midjourney is checked daily against the live service.
- Fastest day
- 735ms
- Slowest day
- 1072ms
- 14-day trend
- Improving-10%
Connect your client
One URL. Every client.
Activate the Connector, copy your link, and paste it into the client you already use. 10 capabilities arrive ready to run.
Preview access · not provider authentication
The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Midjourney, so you can see the experience inside your AI.
It does not authenticate your account with Midjourney. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.
Midjourney Connector
You're all set. Choose your MCP client and follow the setup instructions.
https://edge.vinkius.com/vk_preview_KJmjB4nSYkRoRDgobS5cd1HnWhFpTK9xtc42MEMX/mcpClaude Desktop
Follow the steps below to connect in seconds.
- 1In Claude Desktop, open Settings → Connectors.
- 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
- 3Click Add and start a new chat — Midjourney capabilities are ready to use.
{
"mcpServers": {
"midjourney-ai-generative-image-arts-mcp": {
"url": "https://edge.vinkius.com/vk_preview_KJmjB4nSYkRoRDgobS5cd1HnWhFpTK9xtc42MEMX/mcp"
}
}
}
Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline
Step-by-step instructions for each client are in the guide. How to connect
FAQ
Questions Midjourney owners ask.
- 01
How do I check if my Midjourney image is ready?
Use the get_job capability with the Job ID provided. Your agent will poll the API and report the current state (pending or completed). Once finished, it will return the final image URL or the 2x2 grid depending on your task.
- 02
Can I edit an image by zooming out or panning the camera through the agent?
Absolutely. Use the pan_image and zoom_out_image capabilities with a completed Job ID. Your agent will command Midjourney to expand the canvas or shift the focus in your specified direction, creating professional cinematographic edits.
- 03
What does the 'describe' capability do?
The describe_image capability reverse engineers prompts. Provide an image URL, and your agent will retrieve 4 candidate text descriptions from Midjourney, showing you the exact words and styles used to create that visual concept.
Explore
More in Superpower
HTMLCSSToImage AI Connector
Generate high-quality images and PDFs from HTML/CSS or URLs directly from your AI agent.
ViewRoboflow AI Connector
Manage computer vision workflows — upload images, train models, and manage datasets directly from your AI agen
ViewThe Cat AI Connector
Access the world's largest collection of cat images, search by breed, and manage your favorites or votes direc
ViewVectorizer AI AI Connector
Convert bitmap images (JPG, PNG) into high-quality vector graphics (SVG, EPS, PDF, DXF) using AI-powered traci
View
Suggestions
ImageCharts AI Connector
Generate charts and graphs as images from URL parameters with a simple API that creates data visualizations on
ViewCanva AI Connector
Empower your AI agents to manage Canva designs, upload branding assets, and trigger automatic exports directly
ViewUnsplash AI Connector
Access millions of high-resolution images — search photos, manage collections, and track download statistics d
ViewGrid AI Connector
Turn spreadsheet data into interactive dashboards and visual stories that make numbers accessible to every sta
View
