An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Midjourney to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Turn text prompts into high-resolution visuals through your AI agent.

Ask AI about this Connector

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.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 9 capabilities

We ship only the actions that matter.

Capability set01 / 03

01-03

3 capabilities in this set.

Part of 9 available through Midjourney.

  1. 01

    Blend

    This capability merges multiple images into a single composition. You provide image URLs and an optional text prompt to guide the final look.

  2. 02

    Inpaint

    This capability edits specific parts of a generated image. It uses a mask to change a selected region while keeping the rest of the image intact.

  3. 03

    Reroll

    This capability generates four new images using your existing prompt. Use it when the initial results don't hit the mark.

Capability set02 / 03

04-06

3 capabilities in this set.

Part of 9 available through Midjourney.

  1. 04

    Upscale

    This capability increases the resolution of a generated image. It takes one of the initial four images and returns a high-resolution URL.

  2. 05

    Variation

    This capability creates new versions of an existing image. It's the best way to explore different interpretations of a concept you've already started.

  3. 06

    Describe

    This capability reverse-engineers a prompt from an image. It analyzes a picture and tells you the text needed to recreate that style or composition.

Capability set03 / 03

07-09

3 capabilities in this set.

Part of 9 available through Midjourney.

  1. 07

    Get tasks

    This capability lists your recent image generation tasks. It helps you keep track of what's running and find image IDs for further editing.

  2. 08

    Get task status

    This capability checks the progress of a specific generation. It returns the completion percentage and the final image URLs once they are ready.

  3. 09

    Imagine

    This capability starts the image generation process from a text prompt. You can include parameters like aspect ratio or stylization directly in your request.

Real work

What teams actually run

01

Rapid Prototyping

A designer asks the agent to generate several variations of a logo concept to find the right direction.

02

Asset Creation

A blogger uses the agent to create a specific hero image for an article using a detailed text prompt.

03

Style Transfer

A creator uses the describe capability to figure out how to replicate a specific art style in a new prompt.

04

Image Editing

A user asks the agent to inpaint a specific area of a generated image to fix a small detail.

Automate a task

Put Midjourney to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Midjourney works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put Midjourney to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

889ms average. Fast in production.

Midjourney is checked daily against the live service.

Daily averagePeak 1027ms
Oct 3Today
Fastest day
747ms
Slowest day
1027ms
14-day trend
Stable+3%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 9 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.

Connector linkhttps://edge.vinkius.com/vk_preview_GtWGlzERWZpiQgoYZJ3Yk8hyvL5xnzs8QnvjgS2I/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Midjourney capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "midjourney-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_GtWGlzERWZpiQgoYZJ3Yk8hyvL5xnzs8QnvjgS2I/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

Guided setup for Claude? Set up Midjourney in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Midjourney owners hand off.

This MCP is built for creative professionals who want to integrate high-end image generation into their existing AI-driven workflows.

  • 01

    Designers

    They use the agent to rapidly prototype visual concepts and test different styles.

  • 02

    Content Creators

    They generate custom visuals for social media, blogs, or presentations via chat.

  • 03

    Developers

    They integrate Midjourney's capabilities into their own apps or automated workflows.

FAQ

Questions Midjourney owners ask.

  • 01

    How do I use Midjourney with Claude?

    You connect the Midjourney MCP to Claude via Vinkius. Once connected, you can simply ask Claude to generate images using the imagine capability.

  • 02

    Do I need my own Midjourney subscription?

    Yes, you will need to provide your Midjourney API key through Ace Data Cloud to authenticate the connection.

  • 03

    Can I change the aspect ratio of my images?

    Yes, you can include Midjourney parameters like --ar 16:9 directly in your text prompt when using the imagine capability.

  • 04

    How can I see if my image is finished?

    Your agent can use the get_task_status capability to check the progress percentage and retrieve the final image URL once it is ready.

  • 05

    What happens if I don't like the first four images?

    You can tell your agent to use the reroll capability to generate four entirely new images based on the same prompt.

  • 06

    How do I get a Midjourney API key?

    Sign up at Ace Data Cloud and subscribe to the Midjourney Imagine API service. You'll receive an API key that works with this MCP server.

  • 07

    What's the difference between upscale and variation?

    Upscale increases resolution of a specific grid image (1-4) to full quality. Variation creates 4 new creative alternatives based on that image's style and composition. Use upscale for final output, variation for exploration.

  • 08

    How long does image generation take?

    Typically 30-60 seconds. Use get_task_status to check progress. The API returns a task ID immediately, and you can poll for completion or set a callback URL for async notification.

Explore

More in AI Frontier

Suggestions

Connect Midjourney to Claude, Cursor, ChatGPT & more