MidjourneyMCP

midjourney_imagine

Generate AI images from a text prompt, producing a 2x2 grid of four variations. Describe your creative vision to get custom artwork and illustrations.

Instructions

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 vision to visualize
- You need AI-generated artwork or illustrations

For image transformations like upscaling or variations, use midjourney_transform instead.

Returns:
    Task ID and generated image information including URLs, dimensions, and available actions.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`hd`	No	Enable HD output. V8.2 supports HD; V8.1 uses separate SD and HD resolution-based rates.
`mask`	No	Optional Base64-encoded mask image for image-based generation actions.
`mode`	No	Generation mode. 'fast' is recommended and 'relax' is slower but cheaper. 'turbo' is faster on supported versions. V8.2 supports it; V8.1 only supports fast and relax.	fast
`async`	No	Whether to process the request asynchronously.
`prompt`	Yes	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 at night, neon lights, rain, photorealistic', 'Abstract watercolor painting of mountains and clouds'
`quality`	No	Image quality level for versions that support --quality / --q. V8.2 supports it. This parameter is not supported in V8.1.
`timeout`	No	Timeout in seconds for the API to return data. Default is 480.
`version`	No	Midjourney model version to use, e.g. '8.2', '8.1', '8', '7', '6.1'. '8.2' is the latest version and is recommended. Leave unset to use Midjourney's default.
`image_id`	No	Optional image ID for image-based generation actions.
`moodboard`	No	Whether the prompt uses a moodboard. V8.1 bills it at the selected SD/HD resolution rate; V8.0 Alpha uses different premium rules.
`translation`	No	If true, automatically translate non-English prompts to English for better results.
`callback_url`	No	Webhook callback URL for asynchronous notifications. When provided, the API will call this URL when the image is generated.
`split_images`	No	If true, split the 2x2 grid result into 4 separate images returned via sub_image_urls.
`style_reference`	No	Whether the prompt includes --sref style reference. V8.1 bills it at the selected SD/HD resolution rate; V8.0 Alpha uses different premium rules.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

Changed3 schema fields changedv0.1.10Sep 2, 2026

addedInput schema / properties / async

Added value: +{
+  "anyOf": [
+    {
+      "type": "boolean"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Whether to process the request asynchronously.",
+  "title": "Async"
+}

addedInput schema / properties / image_id

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Optional image ID for image-based generation actions.",
+  "title": "Image Id"
+}

addedInput schema / properties / mask

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Optional Base64-encoded mask image for image-based generation actions.",
+  "title": "Mask"
+}

Changed5 schema fields changedv0.1.9Aug 20, 2026

changedInput schema / properties / hd / description

Previous value: -"Enable 2K HD output. V8.1 uses separate SD and HD resolution-based rates; V8.0 Alpha uses different premium rules."New value: +"Enable HD output. V8.2 supports HD; V8.1 uses separate SD and HD resolution-based rates."

changedInput schema / properties / mode / description

Previous value: -"Generation mode. 'fast' is recommended and 'relax' is slower but cheaper. 'turbo' is faster on supported versions, but V8.1 only supports fast and relax."New value: +"Generation mode. 'fast' is recommended and 'relax' is slower but cheaper. 'turbo' is faster on supported versions. V8.2 supports it; V8.1 only supports fast and relax."

changedInput schema / properties / quality / description

Previous value: -"Image quality level for versions that support --quality / --q. This parameter is not supported in V8.1; use hd for higher-resolution V8.1 output."New value: +"Image quality level for versions that support --quality / --q. V8.2 supports it. This parameter is not supported in V8.1."

changedInput schema / properties / version / anyOf

Previous value: -[
-  {
-    "enum": [
-      "5.2",
-      "6",
-      "6.1",
-      "7",
-      "8",
-      "8.1"
-    ],
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "enum": [
+      "5.2",
+      "6",
+      "6.1",
+      "7",
+      "8",
+      "8.1",
+      "8.2"
+    ],
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

changedInput schema / properties / version / description

Previous value: -"Midjourney model version to use, e.g. '8.1', '8', '7', '6.1'. '8.1' is the latest version and is recommended. Leave unset to use Midjourney's default."New value: +"Midjourney model version to use, e.g. '8.2', '8.1', '8', '7', '6.1'. '8.2' is the latest version and is recommended. Leave unset to use Midjourney's default."

Changed5 schema fields changedv0.1.7Aug 6, 2026

changedInput schema / properties / hd / description

Previous value: -"Enable HD mode (V8/V8.1). Generates higher resolution images at 4x cost."New value: +"Enable 2K HD output. V8.1 uses separate SD and HD resolution-based rates; V8.0 Alpha uses different premium rules."

changedInput schema / properties / mode / description

Previous value: -"Generation mode. 'fast' is recommended for most use cases. 'turbo' is faster but uses more credits. 'relax' is slower but cheaper."New value: +"Generation mode. 'fast' is recommended and 'relax' is slower but cheaper. 'turbo' is faster on supported versions, but V8.1 only supports fast and relax."

changedInput schema / properties / moodboard / description

Previous value: -"Whether using moodboard feature (V8 only, multiple reference images). Incurs 4x cost."New value: +"Whether the prompt uses a moodboard. V8.1 bills it at the selected SD/HD resolution rate; V8.0 Alpha uses different premium rules."

changedInput schema / properties / quality / description

Previous value: -"Image quality level. Values: '.25', '.5', '1', '2', '4'. Quality '4' is V8/V8.1 only."New value: +"Image quality level for versions that support --quality / --q. This parameter is not supported in V8.1; use hd for higher-resolution V8.1 output."

changedInput schema / properties / style_reference / description

Previous value: -"Whether the prompt includes --sref style reference. In V8 this incurs 4x cost."New value: +"Whether the prompt includes --sref style reference. V8.1 bills it at the selected SD/HD resolution rate; V8.0 Alpha uses different premium rules."

Addedv0.1.5May 31, 2026
Removedv0.1.4May 24, 2026

Changed4 schema fields changedv0.1.2May 12, 2026

changedInput schema / properties / hd / description

Previous value: -"Enable HD mode (V8 only). Generates higher resolution images at 4x cost. Requires version='8'."New value: +"Enable HD mode (V8/V8.1). Generates higher resolution images at 4x cost."

changedInput schema / properties / quality / description

Previous value: -"Image quality level. For V8: '1' (standard) or '4' (ultra, 4x cost). For older versions: '.25', '.5', or '1'. HD + quality '4' = 16x cost."New value: +"Image quality level. Values: '.25', '.5', '1', '2', '4'. Quality '4' is V8/V8.1 only."

changedInput schema / properties / version / anyOf

Previous value: -[
-  {
-    "enum": [
-      "5.2",
-      "6",
-      "6.1",
-      "7",
-      "8"
-    ],
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "enum": [
+      "5.2",
+      "6",
+      "6.1",
+      "7",
+      "8",
+      "8.1"
+    ],
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

changedInput schema / properties / version / description

Previous value: -"Midjourney model version to use. '8' is the latest V8 Alpha with HD and ultra quality support. Leave unset to use Midjourney's default."New value: +"Midjourney model version to use, e.g. '8.1', '8', '7', '6.1'. '8.1' is the latest version and is recommended. Leave unset to use Midjourney's default."

Changed7 schema fields changedv0.1.1May 4, 2026

addedInput schema / properties / callback_url

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Webhook callback URL for asynchronous notifications. When provided, the API will call this URL when the image is generated.",
+  "title": "Callback Url"
+}

addedInput schema / properties / hd

Added value: +{
+  "default": false,
+  "description": "Enable HD mode (V8 only). Generates higher resolution images at 4x cost. Requires version='8'.",
+  "title": "Hd",
+  "type": "boolean"
+}

addedInput schema / properties / moodboard

Added value: +{
+  "default": false,
+  "description": "Whether using moodboard feature (V8 only, multiple reference images). Incurs 4x cost.",
+  "title": "Moodboard",
+  "type": "boolean"
+}

addedInput schema / properties / quality

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Image quality level. For V8: '1' (standard) or '4' (ultra, 4x cost). For older versions: '.25', '.5', or '1'. HD + quality '4' = 16x cost.",
+  "title": "Quality"
+}

addedInput schema / properties / style_reference

Added value: +{
+  "default": false,
+  "description": "Whether the prompt includes --sref style reference. In V8 this incurs 4x cost.",
+  "title": "Style Reference",
+  "type": "boolean"
+}

addedInput schema / properties / timeout

Added value: +{
+  "anyOf": [
+    {
+      "type": "integer"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Timeout in seconds for the API to return data. Default is 480.",
+  "title": "Timeout"
+}

addedInput schema / properties / version

Added value: +{
+  "anyOf": [
+    {
+      "enum": [
+        "5.2",
+        "6",
+        "6.1",
+        "7",
+        "8"
+      ],
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Midjourney model version to use. '8' is the latest V8 Alpha with HD and ultra quality support. Leave unset to use Midjourney's default.",
+  "title": "Version"
+}

First observedv0.1.0Jan 22, 2026

TDQS

A4.2/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the disclosure burden. It usefully reveals the 2x2 grid output and the return payload including Task ID, URLs, dimensions, and available actions. However, it does not mention billing/credit consumption, expected latency, or asynchronous execution behavior, which are material for an image-generation tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-organized into purpose, usage criteria, alternative routing, and return information. Every sentence adds value, and the structure is front-loaded with the primary action before usage guidance.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex 14-parameter tool with an output schema, the description covers the core invocation path, output format, and sibling routing. Version-specific and async/callback details are already documented in the input schema, so the description does not need to repeat them.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, with detailed descriptions for all 14 parameters including defaults, version notes, and examples. The description adds no new parameter-level semantics beyond emphasizing that the prompt is the core input, which is acceptable because the schema already handles this thoroughly.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: 'Generate AI images from a text prompt using Midjourney.' It clearly positions this as the primary creation tool and distinguishes it from midjourney_transform by noting that transformations like upscaling or variations belong elsewhere.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit 'Use this when' criteria such as creating new images from a text description, visualizing a creative vision, or needing AI-generated artwork. It also names the alternative midjourney_transform for transformation tasks, giving an agent direct routing guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/AceDataCloud/MidjourneyMCP'

If you have feedback or need assistance with the MCP directory API, please join our Discord server