Midjourney Connector for AI agents.
9 live capabilities
Create high-resolution marketing visuals and creative assets through natural conversation.
Waiting for input…
Why people use Midjourney
Midjourney Image Generation for Marketing Teams
This Connector puts the entire Midjourney pipeline inside your AI client. You just describe the scene, and your agent handles the rest. You get a direct path from an idea to a high-resolution image without the constant context switching.
What Vinkius changes
You get a direct bridge from your chat interface to high-end image generation.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 5,900+ Connectors
- Real-world use case 01
Rapid social media asset generation
A social media manager needs 10 unique blog headers.
- Real-world use case 02
Reverse-engineering visual styles
A designer finds a great style but can't replicate it.
- Real-world use case 03
Exploring visual variations
A content creator wants to see 5 different takes on a logo.
Complete set · 9capabilities
The complete Midjourney capability set.
These are the exact actions your AI can choose when you ask it to work with Midjourney.
01—03
3 capabilities in this set.
Part of 9 available through Midjourney.
- 01 Capability
Blend
Combine 2 to 5 image URLs into a single new composition with an optional text prompt.
- 02 Capability
Describe
Turn an existing image into a text prompt to help you recreate similar styles or compositions.
- 03 Capability
Get task status
Check the progress of a generation, get final URLs, and see available actions like upscale or variation.
04—06
3 capabilities in this set.
Part of 9 available through Midjourney.
- 04 Capability
Get tasks
List your recent image generation tasks to find specific IDs for further editing or upscaling.
- 05 Capability
Imagine
Generate high-quality images from text prompts including style modifiers like aspect ratios and versions.
- 06 Capability
Inpaint
Edit a specific region of a generated image using a mask while keeping the rest of the image the same.
07—09
3 capabilities in this set.
Part of 9 available through Midjourney.
- 07 Capability
Reroll
Regenerate 4 new images using the exact same prompt when the initial results don't hit the mark.
- 08 Capability
Upscale
Turn one of the four initial grid images into a high-resolution version for final use.
- 09 Capability
Variation
Create a new set of images based on a specific interpretation of one of your previous results.
Set up in minutes
One URL. Then ask Midjourney to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use Midjourney from the conversation.
Choose your client
Live previewAdvanced clients IDE · CLI
Claude · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_GtWGlzERWZpiQgoYZJ3Yk8hyvL5xnzs8QnvjgS2I/mcp - Step 01
Open Connectors
In Claude Web or Claude Desktop, open Settings and choose Connectors.
- Step 02
Add the URL
Choose Add custom connector, name it Midjourney, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable Midjourney for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_GtWGlzERWZpiQgoYZJ3Yk8hyvL5xnzs8QnvjgS2I/mcp - Step 01
Open MCP settings
On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
- Step 02
Add the URL
Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the Midjourney URL.
- Step 03
Save and start
Save the connection and enable Midjourney in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"midjourney": {
"url": "https://edge.vinkius.com/vk_preview_GtWGlzERWZpiQgoYZJ3Yk8hyvL5xnzs8QnvjgS2I/mcp"
}
}
}- Step 01
Open MCP Settings
Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
- Step 02
Add the server config
Paste the JSON configuration above into the mcp.json file that opens
- Step 03
Save the file
Cursor will automatically detect the new Connector
- Step 04
Start using Midjourney
Open Agent mode in chat and ask: "Using Midjourney, help me...". 9 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"midjourney": {
"url": "https://edge.vinkius.com/vk_preview_GtWGlzERWZpiQgoYZJ3Yk8hyvL5xnzs8QnvjgS2I/mcp"
}
}
}- Step 01
Create MCP config
Create a .vscode/mcp.json file in your project root
- Step 02
Add the server config
Paste the JSON configuration above
- Step 03
Enable Agent mode
Open GitHub Copilot Chat and switch to Agent mode using the dropdown
- Step 04
Start using Midjourney
Ask Copilot: "Using Midjourney, help me...". 9 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"midjourney": {
"url": "https://edge.vinkius.com/vk_preview_GtWGlzERWZpiQgoYZJ3Yk8hyvL5xnzs8QnvjgS2I/mcp"
}
}
}- Step 01
Open MCP Settings
Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
- Step 02
Add the server
Paste the JSON configuration above into mcp_config.json
- Step 03
Save and reload
Windsurf will detect the new server automatically
- Step 04
Start using Midjourney
Open Cascade and ask: "Using Midjourney, help me...". 9 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"midjourney": {
"url": "https://edge.vinkius.com/vk_preview_GtWGlzERWZpiQgoYZJ3Yk8hyvL5xnzs8QnvjgS2I/mcp"
}
}
}- Step 01
Open Cline MCP Settings
Click the Connectors icon in the Cline sidebar panel
- Step 02
Add remote server
Click "Add Connector" and paste the configuration above
- Step 03
Enable the server
Toggle the server switch to ON
- Step 04
Start using Midjourney
Ask Cline: "Using Midjourney, help me...". 9 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add midjourney --transport http "https://edge.vinkius.com/vk_preview_GtWGlzERWZpiQgoYZJ3Yk8hyvL5xnzs8QnvjgS2I/mcp"- Step 01
Install Claude Code
Run npm install -g @anthropic-ai/claude-code if not already installed
- Step 02
Add the Connector
Run the command above in your terminal
- Step 03
Verify the connection
Run claude mcp to list connected servers, or type /mcp inside a session
- Step 04
Start using Midjourney
Ask Claude: "Using Midjourney, show me...". 9 tools are ready
Where the request belongs
Work Midjourney can move forward.
This is for creative leads who need to prototype visuals fast without getting bogged down in prompt engineering, or social media managers who need unique assets for every post.
Art Director
Rapidly prototyping mood boards and visual concepts during client meetings.
Content Creator
Generating custom, high-quality social media assets without hiring a full-time editor.
Web Designer
Creating unique hero images and UI elements by blending existing styles.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse ConnectorsMidjourney AI (Generative Image Arts)
Generate professional AI art via Midjourney. use 'imagine' for text-to-image, upscale grids, and perform camera edits.
Stability AI
Connect your AI to Stability AI's powerful image generation models. Create, upscale, and edit high-quality images directly and efficiently.
Playground AI
Generate, inpaint, upscale, and transform images using Playground AI's powerful models via natural language.
APImage
Search and license editorial photography from one of the world largest press image archives for media and publishing.
Image Router
Route image generation requests to the best AI model automatically based on prompt type, style, and quality requirements.
Adobe Firefly
Generate images and vectors via Adobe Firefly. perform generative fill and expand, create text effects, and remove backgrounds directly from any AI agent.
Bring your own AI
Change the model, client or framework. Keep Midjourney connected.
-
Claude -
ChatGPT -
Gemini -
Cursor -
VS Code -
Windsurf -
ZCode -
Cline -
Zed -
Continue -
Kiro -
Roo Code -
Zencoder -
Goose -
Void -
Augment Code -
Amp -
Qodo -
Tabnine -
Pieces -
Sourcegraph Cody -
JetBrains -
Warp -
Amazon Q -
Antigravity -
BoltAI -
Raycast -
Jan -
LM Studio -
AnythingLLM -
Open WebUI -
Msty -
Cherry Studio -
LibreChat -
TypingMind -
Chorus -
5ire -
n8n -
LangChain -
LlamaIndex -
CrewAI -
Vercel AI SDK
Before you connect
Questions about Midjourney.
The practical details behind the request, access and result.
How do I use Midjourney MCP to create images?
You just describe the image you want to see in plain English to your AI client. The Connector sends that request to Midjourney and provides you with the results directly in your chat.
Can Midjourney MCP upscale my images?
Yes, you can ask your agent to upscale any of the generated images. It will take the low-resolution thumbnail and return a link to the full-resolution version.
How does Midjourney MCP handle different aspect ratios?
Your agent can automatically include specific modifiers like aspect ratios in the background. You just tell it you want a wide or tall image, and it handles the technical parameters.
Can I use Midjourney MCP to edit parts of an image?
You can use the inpaint feature to modify specific areas. Just tell your agent which part of the image needs changing, and it will update only that section.
Does Midjourney MCP track my generation progress?
Yes, it monitors your active tasks. Your agent can check the status of a generation and notify you the moment the final images are ready for download.
How can I get a prompt from an image using Midjourney MCP?
You can provide a link to any image, and the Connector will reverse-engineer it into a text prompt. This is perfect for finding the right words to recreate a specific style.
Is Midjourney MCP good for social media content?
It is excellent for creating unique, high-quality visual content. You can generate, blend, and vary images rapidly to keep your social feeds looking fresh and professional.
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 Connector.
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.
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.
One connection away
Give your agent a direct line to Midjourney.
Connect Midjourney once. Keep it beside 5,900+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available