Midjourney

acedatacloud/midjourneymcp

Connects Claude and other MCP clients to Midjourney's image and video generation through the AceDataCloud API. Exposes 15 tools covering the full creative workflow: imagine for text-to-image, transform for upscaling and variations, blend for combining images, describe for reverse prompting, and edit for masked modifications. Also handles video generation and extension, reference-based creation, seed extraction, and task tracking. Hosted endpoint means no local setup, just drop in your AceDataCloud token and start generating. Useful when you want AI image workflows directly in your chat or editor without switching to Discord or the Midjourney web interface.

GitHub stars: 18
tools: 15
auth: Secret needed
transport: STDIO, HTTP
env var: 1
last updated: Nov 7, 2026

View on GitHub

Tools

15 tools

Public tool metadata for what this MCP can expose to an agent.

midjourney_describeGet AI-generated descriptions of an image. This analyzes an image and returns 4 alternative text descriptions that could be used as prompts to recreate similar images with Midjourney. Use this when: - You want to understand what prompts might create a similar image - You want...1 params

Get AI-generated descriptions of an image. This analyzes an image and returns 4 alternative text descriptions that could be used as prompts to recreate similar images with Midjourney. Use this when: - You want to understand what prompts might create a similar image - You want...

Parameters* required

image_urlstring

URL of the image to describe. Must be a direct image URL (JPEG, PNG, GIF, etc.), not a web page containing an image.

midjourney_editEdit an existing image using Midjourney. This allows you to modify an existing image based on a text prompt, optionally using a mask to specify which regions to edit. Use this when: - You want to modify an existing image with AI - You want to add or change elements in an image...6 params

Edit an existing image using Midjourney. This allows you to modify an existing image based on a text prompt, optionally using a mask to specify which regions to edit. Use this when: - You want to modify an existing image with AI - You want to add or change elements in an image...

Parameters* required

callback_urlvalue

Webhook callback URL for asynchronous notifications. When provided, the API will call this URL when the edit is complete.

image_urlstring

URL of the image to edit. Must be a direct image URL (not a web page).

maskstring

Optional Base64-encoded mask image. White areas indicate regions to edit and regenerate.default:

modestring

Generation mode. 'fast' is recommended.one of fast · relax · turbodefault: fast

promptstring

Description of how to edit the image. Examples: 'A cat sitting on a table', 'Add a sunset in the background', 'Make it look like a watercolor painting'

split_imagesboolean

If true, split the result into separate images returned via sub_image_urls.default: false

midjourney_imagineGenerate AI images from a text prompt using Midjourney. This is the primary way to create images - describe what you want and Midjourney will generate a 2x2 grid of 4 image variations. Use this when: - You want to create new images from a text description - You have a creative...11 params

Generate AI images from a text prompt using Midjourney. This is the primary way to create images - describe what you want and Midjourney will generate a 2x2 grid of 4 image variations. Use this when: - You want to create new images from a text description - You have a creative...

Parameters* required

callback_urlvalue

Webhook callback URL for asynchronous notifications. When provided, the API will call this URL when the image is generated.

hdboolean

Enable HD mode (V8 only). Generates higher resolution images at 4x cost. Requires version='8'.default: false

modestring

Generation mode. 'fast' is recommended for most use cases. 'turbo' is faster but uses more credits. 'relax' is slower but cheaper.one of fast · relax · turbodefault: fast

moodboardboolean

Whether using moodboard feature (V8 only, multiple reference images). Incurs 4x cost.default: false

promptstring

Description of the image to generate. Be descriptive about style, subject, lighting, and composition. Examples: 'A majestic lion in a savanna at sunset, cinematic lighting', 'Cyberpunk city street...

qualityvalue

Image quality level. For V8: '1' (standard) or '4' (ultra, 4x cost). For older versions: '.25', '.5', or '1'. HD + quality '4' = 16x cost.

split_imagesboolean

If true, split the 2x2 grid result into 4 separate images returned via sub_image_urls.default: false

style_referenceboolean

Whether the prompt includes --sref style reference. In V8 this incurs 4x cost.default: false

timeoutvalue

Timeout in seconds for the API to return data. Default is 480.

translationboolean

If true, automatically translate non-English prompts to English for better results.default: false

versionvalue

Midjourney model version to use. '8' is the latest V8 Alpha with HD and ultra quality support. Leave unset to use Midjourney's default.

midjourney_transformTransform an existing Midjourney image with various operations. This allows you to upscale, create variations, zoom, or pan existing images generated by Midjourney. Use this when: - You want to upscale one of the 4 images from a generation - You want to create variations of a...5 params

Transform an existing Midjourney image with various operations. This allows you to upscale, create variations, zoom, or pan existing images generated by Midjourney. Use this when: - You want to upscale one of the 4 images from a generation - You want to create variations of a...

Parameters* required

actionstring

Transformation action to perform. Options include: - upscale1/2/3/4: Upscale one of the 4 images (top-left=1, top-right=2, bottom-left=3, bottom-right=4) - upscale_2x/4x: Further upscale an already...one of generate · upscale1 · upscale2 · upscale3 · upscale4 · upscale_2x

image_idstring

ID of the image to transform. This is the 'image_id' field from a previous generation result.

maskstring

Base64-encoded mask image for variation_region action. White areas indicate regions to regenerate.default:

modestring

Generation mode for the transformation.one of fast · relax · turbodefault: fast

promptstring

Optional prompt for the transformation. Used with variation_region action.default:

midjourney_blendBlend multiple images together using Midjourney. This allows you to combine 2-5 images into a new creative fusion. Use this when: - You want to merge elements from multiple images - You want to create composite images - You want to blend styles or subjects together Example: -...3 params

Blend multiple images together using Midjourney. This allows you to combine 2-5 images into a new creative fusion. Use this when: - You want to merge elements from multiple images - You want to create composite images - You want to blend styles or subjects together Example: -...

Parameters* required

image_urlsarray

List of image URLs to blend together. Supports 2-5 images. Images should be pure image URLs (not web pages containing images).

modestring

Generation mode.one of fast · relax · turbodefault: fast

promptstring

Description of how to blend the images. Examples: 'The bear is holding the chainsaw', 'Combine the face with the background'default:

midjourney_with_referenceGenerate images using a reference image as inspiration. This allows you to use an existing image as a starting point and modify it based on your prompt description. Use this when: - You want to reimagine an existing image with modifications - You want to change the style of an...3 params

Generate images using a reference image as inspiration. This allows you to use an existing image as a starting point and modify it based on your prompt description. Use this when: - You want to reimagine an existing image with modifications - You want to change the style of an...

Parameters* required

modestring

Generation mode.one of fast · relax · turbodefault: fast

promptstring

Description of how to modify or reimagine the reference image. Examples: 'an illustration of a car parked on the beach --iw 2', 'in the style of Van Gogh'

reference_image_urlstring

URL of the reference image to use as a base. Must be a direct image URL (not a web page).

midjourney_list_actionsList all available Midjourney API actions and corresponding tools. Reference guide for what each action does and which tool to use. Helpful for understanding the full capabilities of the Midjourney MCP. Returns: Categorized list of all actions and their corresponding tools.

List all available Midjourney API actions and corresponding tools. Reference guide for what each action does and which tool to use. Helpful for understanding the full capabilities of the Midjourney MCP. Returns: Categorized list of all actions and their corresponding tools.

No parameter schema in public metadata yet.

midjourney_get_prompt_guideGet guidance on writing effective prompts for Midjourney. Shows how to structure prompts and use parameters for best results. Following this guide helps Midjourney understand your creative vision. Returns: Complete guide with prompt structure, parameters, and examples.

Get guidance on writing effective prompts for Midjourney. Shows how to structure prompts and use parameters for best results. Following this guide helps Midjourney understand your creative vision. Returns: Complete guide with prompt structure, parameters, and examples.

No parameter schema in public metadata yet.

midjourney_list_transform_actionsList all available transformation actions for Midjourney images. Reference guide for transform actions used with midjourney_transform tool. Returns: Detailed list of all transformation actions and when to use them.

List all available transformation actions for Midjourney images. Reference guide for transform actions used with midjourney_transform tool. Returns: Detailed list of all transformation actions and when to use them.

No parameter schema in public metadata yet.

midjourney_get_seedGet the seed value of a previously generated Midjourney image. The seed is a numeric value that controls the randomness of generation. Using the same seed with the same prompt will produce similar results, which is useful for reproducible generation or fine-tuning prompts. Use...1 params

Get the seed value of a previously generated Midjourney image. The seed is a numeric value that controls the randomness of generation. Using the same seed with the same prompt will produce similar results, which is useful for reproducible generation or fine-tuning prompts. Use...

Parameters* required

image_idstring

The ID of the generated image to get the seed for. This is the 'image_id' field from a previous imagine result.

midjourney_get_taskQuery the status and result of a Midjourney generation task. Use this to check if a generation is complete and retrieve the resulting image/video URLs and metadata. Use this when: - You want to check if a generation has completed - You need to retrieve URLs from a previous gen...1 params

Query the status and result of a Midjourney generation task. Use this to check if a generation is complete and retrieve the resulting image/video URLs and metadata. Use this when: - You want to check if a generation has completed - You need to retrieve URLs from a previous gen...

Parameters* required

task_idstring

The task ID returned from a generation request. This is the 'task_id' field from any midjourney_imagine, midjourney_describe, midjourney_edit, or midjourney_generate_video tool response.

midjourney_get_tasks_batchQuery multiple Midjourney generation tasks at once. Efficiently check the status of multiple tasks in a single request. More efficient than calling midjourney_get_task multiple times. Use this when: - You have multiple pending generations to check - You want to get status of s...1 params

Query multiple Midjourney generation tasks at once. Efficiently check the status of multiple tasks in a single request. More efficient than calling midjourney_get_task multiple times. Use this when: - You have multiple pending generations to check - You want to get status of s...

Parameters* required

task_idsarray

List of task IDs to query. Maximum recommended batch size is 50 tasks.

midjourney_translateTranslate Chinese text to English for use as Midjourney prompts. Midjourney works best with English prompts. This tool helps translate Chinese descriptions to English, optimized for image generation. Use this when: - You have a Chinese description that needs translation - You...1 params

Translate Chinese text to English for use as Midjourney prompts. Midjourney works best with English prompts. This tool helps translate Chinese descriptions to English, optimized for image generation. Use this when: - You have a Chinese description that needs translation - You...

Parameters* required

contentstring

Chinese text to translate to English. This is useful for converting Chinese prompts to English for better Midjourney results.

midjourney_generate_videoGenerate a video from text prompt and reference image using Midjourney. This creates an AI-generated video based on your description and a starting frame image. You can optionally specify an ending frame for more control. Use this when: - You want to animate a still image - Yo...7 params

Generate a video from text prompt and reference image using Midjourney. This creates an AI-generated video based on your description and a starting frame image. You can optionally specify an ending frame for more control. Use this when: - You want to animate a still image - Yo...

Parameters* required

callback_urlvalue

Webhook callback URL for asynchronous notifications. When provided, the API will call this URL when the video is generated.

end_image_urlstring

Optional URL of the last frame reference image. Use this to control where the video ends.default:

image_urlstring

URL of the first frame reference image. This image will be used as the starting point for the video.

loopboolean

If true, generate a looping video where the end seamlessly connects to the beginning.default: false

modestring

Generation mode. 'fast' is recommended for most use cases.one of fast · relax · turbodefault: fast

promptstring

Description of the video to generate. Examples: 'A cat walking on a table', 'Ocean waves crashing on the shore', 'Timelapse of clouds moving'

resolutionstring

Video resolution. '720p' or '480p'.one of 480p · 720pdefault: 720p

midjourney_extend_videoExtend an existing Midjourney video to make it longer. This allows you to continue a previously generated video by adding more frames based on your prompt description. Use this when: - You want to make a video longer - You want to continue the story or motion from an existing...6 params

Extend an existing Midjourney video to make it longer. This allows you to continue a previously generated video by adding more frames based on your prompt description. Use this when: - You want to make a video longer - You want to continue the story or motion from an existing...

Parameters* required

callback_urlvalue

Webhook callback URL for asynchronous notifications. When provided, the API will call this URL when the video extension is complete.

end_image_urlstring

Optional URL of an image to use as the final frame of the extended video.default:

modestring

Generation mode.one of fast · relax · turbodefault: fast

promptstring

Description for the video extension. This guides how the video should continue.

video_idstring

ID of the video to extend. This is the 'video_id' field from a previous video generation result.

video_indexinteger

Index of the video to extend from the video_urls array. 0-indexed, default is 0 (first video).default: 0

Configuration

ACEDATACLOUD_API_TOKEN*secret

API token from Ace Data Cloud (https://platform.acedata.cloud)

Readme

MidjourneyMCP

A Model Context Protocol (MCP) server for AI image and video generation using Midjourney through the AceDataCloud API.

Generate AI images, videos, and manage creative projects directly from Claude, VS Code, or any MCP-compatible client.

Features

View the full README on GitHub

Details

Repository: github.com/acedatacloud/midjourneymcp
Website: platform.acedata.cloud/services/d87e5e99-b797-4ade-9e73-b896896b0461?utm_source=mcp_registry&utm_medium=referral&utm_campaign=evergreen&utm_content=midjourney_mcp_listing_guide
Category: Design & Creative
Package: mcp-midjourney
Transport: STDIO, HTTP
Auth: Required
Registry: MCP registry, active

Related Design & Creative MCP servers

View all

Vap Evapagentmedia/vap-showcaseAI image, video & music generation. Flux, Veo 3.1, Suno V5. Free tier included.0stars

React Render Profile Mcpvola-trebla/react-render-profile-mcpDecodes React DevTools Profiler exports into render summaries and memoization advice for AI agents.2stars