MCP For Claude Marketplace
Midjourney AI (Generative Image Arts)

Midjourney AI (Generative Image Arts) MCP Connector for Claude

A+

Generate professional AI art via Midjourney — use 'imagine' for text-to-image, upscale grids, and perform camera edits.

10 tools Official Updated Oct 1, 2026 Official Vinkius Partner
More Details Connect to Claude

Connect your Midjourney account to any AI agent and take full control of state-of-the-art generative art production and professional creative tools through natural conversation.

What you can do

  • Cinematic Imagine — Generate high-fidelity AI images from scenic descriptions using Midjourney's latest generative models directly from your agent
  • Precision Upscaling — Extract and upscale specific tiles from your 2x2 generation grids to retrieve high-resolution final renders securely
  • Visual Variation — Create brand new structural branches from existing grid images to iterate on visual concepts and aesthetic directions
  • Camera Control (Pan & Zoom) — Direct your AI shots with specific directional movements (up, down, left, right) or widen perspective using dynamic zoom out levels
  • Image Description — Reverse engineer prompts from any public image URL, retrieving 4 candidate text descriptions to understand visual concepts natively
  • Multi-Image Blending — Merge between 2 and 5 source images into a single unique composition, bridging distinct artistic styles flawlessly
  • Task Orchestration — Manage asynchronous generation jobs, poll for status updates (pending, completed), and monitor your account's job history in real-time

How it works

  1. Subscribe to this server
  2. Enter your Midjourney API Key
  3. Start generating world-class art from Claude, Cursor, or any MCP-compatible client

Who is this for?

  • Digital Artists & Designers — rapid-prototype visual concepts and aesthetic directions through natural conversation without manual prompt entry
  • Creative Directors — generate high-quality moodboards and storyboard frames by commanding your agent to iterate on variations and blends
  • Marketing Teams — produce photorealistic assets and cinematic backgrounds directly from your workspace terminal for high-speed design workflows
generative-arttext-to-imageai-designcreative-toolsupscaling

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

reroll_job

Re-run identical prompt arguments dropping new sets of outputs

blend_images

Pass absolute valid URLs delimited strictly by commas. Blend 2-5 explicit images into a new unique composition

describe_image

Reverse engineer text descriptions from an input image via Midjourney

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

generate_variation

Returns a new Job. Create variant branches from a specific Midjourney grid image

get_job

DO NOT loop aggressively, sleep in between. Get the active execution status of an ongoing Midjourney job

zoom_out_image

Widen the perspective zooming out explicitly

list_jobs

List recent history representing previously executed Midjourney prompts

pan_image

Extrapolate frame borders panning natively over a direction

upscale_image

Polled async. Extract and upscale a single specific tile off a 2x2 grid

See how to talk to your AI agent using Midjourney AI (Generative Image Arts).

Generate a futuristic cyberpunk city at sunset with neon reflections in 16:9

Generating image… I've triggered the Midjourney imagine task with your prompt and a 16:9 aspect ratio. Your Job ID is 'mj-98765'. I'm monitoring the process. High-fidelity textures and lighting are being computed. I'll provide the 2x2 grid URL as soon as it's ready.

Upscale the first image from grid ID 'mj-98765'

Upscaling tile 1… I've triggered the high-resolution render for your first choice. This will isolate the image and apply advanced AI detail enhancement. I'll provide the final high-res URL once the upscale job completes.

Describe the contents of this image: [url]

Analyzing visual concepts… I've retrieved 4 candidate prompts from Midjourney: 1) 'Minimalist architectural sketch in charcoal', 2) 'Brutalist concrete building perspective', 3) 'Abstract geometric shadows on stone', and 4) 'Architectural blueprint style'. Would you like to use any of these to generate a new variation?

Use the `get_job` tool 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.

Related Connectors

ImageCharts

ImageCharts MCP

10 tools Official

Generate charts and graphs as images from URL parameters with a simple API that creates data visualizations on the fly.

A+ View details →
Unsplash

Unsplash MCP

28 tools Official

Access millions of high-resolution images — search photos, manage collections, and track download statistics directly from any AI agent.

A+ View details →
Grid

Grid MCP

12 tools Official

Turn spreadsheet data into interactive dashboards and visual stories that make numbers accessible to every stakeholder.

A+ View details →
Chainlit

Chainlit MCP

6 tools Official

Empower your AI agents to audit chat threads, analyze model steps, and track LLM observability metrics securely.

A+ View details →