mcp-minimax

minimax_generate_video_from_images

Create video clips from static images: provide one first-frame image or multiple reference images plus a motion/style prompt, and specify duration, aspect ratio, and resolution.

Instructions

Generate from one first-frame image or multiple reference images.

Single image uses first_frame mode; multiple images use reference_image mode.
The two modes are mutually exclusive per MiniMax H3 v2 API contract.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`async`	No	Return a task_id immediately for minimax_get_task polling.
`model`	No	MiniMax H3 model name.	MiniMax-H3
`ratio`	No	Output aspect ratio.	16:9
`prompt`	Yes	Required motion and style guidance.
`duration`	No	Integer output duration from 4 to 15 seconds.
`image_urls`	Yes	Public image URLs.
`resolution`	No	Output resolution: 768P or 2K.	2K
`callback_url`	No	Optional public webhook URL for the final result.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed15 schema fields changedv0.1.1Aug 21, 2026

addedInput schema / properties / async

Added value: +{
+  "default": true,
+  "description": "Return a task_id immediately for minimax_get_task polling.",
+  "title": "Async",
+  "type": "boolean"
+}

changedInput schema / properties / image_urls / description

Previous value: -"One to nine public reference image URLs."New value: +"Public image URLs."

removedInput schema / properties / image_urls / maxItems
```
Removed value: -9
```

changedInput schema / properties / model / const

Previous value: -"minimax-h3"New value: +"MiniMax-H3"

changedInput schema / properties / model / default

Previous value: -"minimax-h3"New value: +"MiniMax-H3"

removedInput schema / properties / prompt / anyOf

Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]

removedInput schema / properties / prompt / default
```
Removed value: -null
```

changedInput schema / properties / prompt / description

Previous value: -"Optional motion, camera, and style guidance."New value: +"Required motion and style guidance."

addedInput schema / properties / prompt / maxLength
```
Added value: +7000
```
addedInput schema / properties / prompt / minLength
```
Added value: +1
```
addedInput schema / properties / prompt / type
```
Added value: +"string"
```

changedInput schema / properties / ratio / description

Previous value: -"Output aspect ratio: 16:9 or 9:16."New value: +"Output aspect ratio."

changedInput schema / properties / ratio / enum

Previous value: -[
-  "16:9",
-  "9:16"
-]New value: +[
+  "adaptive",
+  "21:9",
+  "16:9",
+  "4:3",
+  "1:1",
+  "3:4",
+  "9:16"
+]

addedInput schema / properties / resolution

Added value: +{
+  "default": "2K",
+  "description": "Output resolution: 768P or 2K.",
+  "enum": [
+    "768P",
+    "2K"
+  ],
+  "title": "Resolution",
+  "type": "string"
+}

changedInput schema / required

Previous value: -[
-  "image_urls"
-]New value: +[
+  "image_urls",
+  "prompt"
+]

First observedv0.1.0Aug 7, 2026

TDQS

A3.6/5.0

Behavior3/5

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

The description mentions 'per MiniMax H3 v2 API contract', hinting at API-specific behavior, but does not disclose potential side effects (e.g., cost, processing time) or return behavior. Since annotations are absent, it carries the full burden but falls short of full transparency.

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 concise, using three short sentences to convey the core functionality and mode constraints. Every sentence adds value, with no redundant or verbose content.

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?

The description covers the essential aspects: what the tool does (generate video from images), the two input types, and the mutual exclusivity. It is sufficient for basic usage, though it could mention typical use cases or limitations (e.g., only supports certain models).

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?

The description does not add new information beyond the schema, which already covers parameters like image_urls, prompt, ratio, duration, etc. However, by clarifying the mode distinction, it indirectly helps interpret the image_urls parameter. The schema coverage is 100%, so the description only slightly enhances understanding.

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

Purpose4/5

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

The description clearly states the tool generates videos from images, distinguishing it from text/audio generation siblings by mentioning 'first-frame image' and 'reference images'. It specifies the two modes, making the purpose concrete.

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

Usage Guidelines3/5

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

It explains the two modes (first_frame vs reference_image) and notes they are mutually exclusive, which guides usage. However, it does not explicitly compare with sibling tools like generate_video_from_text or generate_video_from_audio, so when to choose this tool over others is implied rather than stated.

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

Deploy Server