grok-imagine-mcp

image_to_video

Convert a source image into a video with custom prompt, motion style, duration, resolution, and aspect ratio, returning a task ID and output URLs.

Instructions

Create a Grok Imagine task on RunAPI (image to video). Returns a task id, status, and output URLs.

Input Schema

TableJSON Schema

Name	Required	Description
`wait`	No	Poll until the task reaches a terminal status.
`index`	No	Zero-based source image index; used only with source_task_id.
`model`	No	RunAPI model slug for this model line.
`prompt`	No	Optional video generation prompt.
`timeout_ms`	No
`aspect_ratio`	No	Output aspect ratio.
`callback_url`	No	Webhook URL for terminal Task delivery.
`motion_style`	No	Video motion style; spicy requires source_task_id.
`source_task_id`	No	Prior Grok Imagine text-to-image Task ID; provide this or source_image_url, but not both.
`duration_seconds`	No	Output duration in seconds.
`poll_interval_ms`	No
`source_image_url`	No	Public source image URL; provide this or source_task_id, but not both.
`output_resolution`	No	Output resolution.
`reference_image_urls`	No	Not accepted by this model.
`enable_safety_checker`	No	Enable content safety checks.

Schema Changelog

Changes observed during successful MCP inspections.

Changed9 schema fields changedv0.1.13Aug 26, 2026

removedInput schema / additionalProperties
```
Removed value: -false
```

addedInput schema / properties / aspect_ratio / anyOf

Added value: +[
+  {
+    "const": "2:3",
+    "type": "string"
+  },
+  {
+    "const": "3:2",
+    "type": "string"
+  },
+  {
+    "const": "1:1",
+    "type": "string"
+  },
+  {
+    "const": "16:9",
+    "type": "string"
+  },
+  {
+    "const": "9:16",
+    "type": "string"
+  },
+  {
+    "const": "auto",
+    "type": "string"
+  }
+]

removedInput schema / properties / aspect_ratio / enum

Removed value: -[
-  "2:3",
-  "3:2",
-  "1:1",
-  "16:9",
-  "9:16",
-  "auto"
-]

removedInput schema / properties / aspect_ratio / type
```
Removed value: -"string"
```

addedInput schema / properties / output_resolution / anyOf

Added value: +[
+  {
+    "const": "480p",
+    "type": "string"
+  },
+  {
+    "const": "720p",
+    "type": "string"
+  },
+  {
+    "const": "1080p",
+    "type": "string"
+  }
+]

removedInput schema / properties / output_resolution / enum
```
Removed value: -[
-  "480p",
-  "720p"
-]
```
removedInput schema / properties / output_resolution / type
```
Removed value: -"string"
```
addedInput schema / properties / poll_interval_ms / maximum
```
Added value: +9007199254740991
```
addedInput schema / properties / timeout_ms / maximum
```
Added value: +9007199254740991
```

Changed14 schema fields changedv0.1.11Aug 5, 2026

addedInput schema / properties / aspect_ratio / description
```
Added value: +"Output aspect ratio."
```

changedInput schema / properties / aspect_ratio / enum

Previous value: -[
-  "2:3",
-  "3:2",
-  "1:1",
-  "16:9",
-  "9:16"
-]New value: +[
+  "2:3",
+  "3:2",
+  "1:1",
+  "16:9",
+  "9:16",
+  "auto"
+]

addedInput schema / properties / callback_url

Added value: +{
+  "description": "Webhook URL for terminal Task delivery.",
+  "type": "string"
+}

addedInput schema / properties / duration_seconds

Added value: +{
+  "description": "Output duration in seconds.",
+  "maximum": 30,
+  "minimum": 6,
+  "type": "number"
+}

addedInput schema / properties / enable_safety_checker

Added value: +{
+  "description": "Enable content safety checks.",
+  "type": "boolean"
+}

addedInput schema / properties / index

Added value: +{
+  "description": "Zero-based source image index; used only with source_task_id.",
+  "maximum": 5,
+  "minimum": 0,
+  "type": "number"
+}

changedInput schema / properties / model / enum

Previous value: -[
-  "grok-imagine-image-to-video"
-]New value: +[
+  "grok-imagine-image-to-video",
+  "grok-imagine-video-1.5-fast",
+  "grok-imagine-video-1.5-preview"
+]

addedInput schema / properties / motion_style / description

Added value: +"Video motion style; spicy requires source_task_id."

removedInput schema / properties / motion_style / enum

Removed value: -[
-  "fun",
-  "normal",
-  "spicy"
-]

addedInput schema / properties / output_resolution / description
```
Added value: +"Output resolution."
```

addedInput schema / properties / prompt

Added value: +{
+  "description": "Optional video generation prompt.",
+  "maxLength": 5000,
+  "type": "string"
+}

addedInput schema / properties / reference_image_urls

Added value: +{
+  "description": "Not accepted by this model.",
+  "items": {},
+  "type": "array"
+}

addedInput schema / properties / source_image_url

Added value: +{
+  "description": "Public source image URL; provide this or source_task_id, but not both.",
+  "type": "string"
+}

addedInput schema / properties / source_task_id

Added value: +{
+  "description": "Prior Grok Imagine text-to-image Task ID; provide this or source_image_url, but not both.",
+  "type": "string"
+}

First observedv0.1.0Jun 24, 2026

TDQS

C2.9/5.0

Behavior2/5

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

No annotations are provided, so the description carries the full burden of disclosing behavior. It states the return payload (task id, status, output URLs), which is useful, but it omits critical behavioral details such as the asynchronous nature of task creation, the need for polling or waiting (evident from wait, poll_interval_ms, timeout_ms parameters), or the role of webhook callbacks. This is a significant gap for an operation that likely returns before completion.

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 a single, compact sentence that immediately states the core function and the return value. It contains zero filler and is perfectly front-loaded. This is an exemplary level of conciseness for a tool description.

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

Completeness2/5

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

For a tool with 15 parameters, no output schema, and no annotations, the description is far too minimal. It lacks workflow context (e.g., that this is an async task, that you need a source image either via URL or prior task, the role of callbacks, or how to interpret the status). The agent is left with only the raw parameter schema to figure out how to correctly invoke the tool, which is insufficient for a tool this complex.

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 high (87%), so most parameters are already documented in the schema. The tool description adds no additional parameter insight beyond what the schema provides. Given the baseline for high coverage is 3, and the description adds nothing more, a 3 is appropriate here.

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 verb 'Create', the resource 'Grok Imagine task', and the specific mode 'image to video', which differentiates it from sibling tools like text_to_image and text_to_video. It also mentions the return values (task id, status, output URLs). The only weakness is that it doesn't explicitly name sibling alternatives, leaving the distinction to inference from the name and context.

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

Usage Guidelines2/5

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

The description provides no guidance on when to use this tool versus the alternatives (e.g., text_to_video or extend_video). While the schema hints at constraints like 'provide this or source_image_url, but not both', the top-level description offers no context about prerequisites, input requirements, or when this tool is the right choice. The agent must rely on the parameter schemas and siblings to infer usage.

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

Deploy Server

image_to_video

Instructions

Input Schema

Schema Changelog

TDQS

Other Tools