Midjourney

Midjourney MCP Connector for Claude

A+

AI image generation — create, upscale, vary, and blend images using Midjourney's Imagine API.

9 tools Official Updated Jun 28, 2026 Official Vinkius Partner

Connect Midjourney image generation to any AI agent and create stunning visuals through natural conversation. Generate images from text prompts, upscale to high resolution, create variations, blend images, and even reverse-engineer prompts from existing images.

What you can do

  • Text-to-Image — Generate high-quality images from descriptive prompts
  • Upscale — Enhance any of the 4 grid images to full resolution
  • Variations — Explore creative alternatives based on any generated image
  • Blend — Combine 2-5 images into a new composition
  • Describe — Reverse-engineer a prompt from any image
  • Inpaint — Edit specific regions of images with masks
  • Task Monitoring — Track generation progress and retrieve completed images

How it works

  1. Subscribe to this server
  2. Enter your Midjourney API key (via Ace Data Cloud)
  3. Start generating images from Claude, Cursor, or any MCP client

Who is this for?

  • Designers — Rapidly prototype visual concepts and explore variations
  • Content Creators — Generate custom images for social media, blogs, and presentations
  • Developers — Integrate AI image generation into apps and workflows
generative-aitext-to-imageimage-upscalingvisual-contentprompt-engineeringcreative-automation

9 tools expose this connector's capabilities to your AI agent.

blend

Provide URLs of existing images to blend together. Optionally add a text prompt to guide the blend. Blend multiple images together into one composition

describe

Useful for understanding how to recreate styles and compositions. Generate a text prompt from an image (reverse engineer)

get_task_status

Returns progress percentage, image URLs when ready, and available actions (upscale/variation). Check the status of an image generation task

get_tasks

Useful for monitoring ongoing generations and finding image IDs for upscale/variation. List recent image generation tasks

imagine

The prompt should be in English and can include style modifiers like "--ar 16:9" for aspect ratio, "--v 6" for version, "--s" for stylization. Returns a task ID and thumbnail URL. Use the task ID to check generation progress. Generate an image from text prompt using Midjourney

inpaint

The rest of the image remains unchanged. Edit a specific region of a generated image using a mask

reroll

Useful when none of the initial 4 images are satisfactory. Regenerate 4 new images with the same prompt

upscale

Returns the upscaled image URL. Upscale one of the 4 generated images to higher resolution

variation

Useful for exploring different interpretations of a concept. Create a variation of one of the 4 generated images

See how to talk to your AI agent using Midjourney.

Generate an image of a cyberpunk city at sunset, 16:9 aspect ratio.

🎨 Image generation started! Task ID: mj_abc123. Check progress with get_task_status. Typical generation time: 30-60 seconds.

Upscale image position 2 from the last generation.

🔍 Image upscaled successfully! Full resolution image URL: https://cdn.midjourney.com/... You can now download or share this image.

Describe this image and tell me what prompt would create it: https://example.com/art.jpg

📝 Generated prompt: 'ethereal watercolor painting of a lone wolf howling at a blood moon, dark forest silhouette, mystical atmosphere --ar 16:9 --v 6'. Use this prompt with imagine to recreate a similar image.

Sign up at [Ace Data Cloud](https://acedata.cloud/) and subscribe to the Midjourney Imagine API service. You'll receive an API key that works with this MCP server.

Related Connectors