@runapi.ai/veo-3-1-mcp

text_to_video

Generate videos from text prompts via Veo 3.1 on RunAPI. Submit a prompt to create a task and receive a task ID, status, and output URLs.

Instructions

Create a Veo 3.1 task on RunAPI (text to video). Returns a task id, status, and output URLs.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "text_to_video"
  }
}

Input Schema

Name	Required	Description
`wait`	No	Poll until the task reaches a terminal status.
`model`	No	RunAPI model slug for this model line.
`seeds`	No	Declared type: integer.
`prompt`	No	Declared type: string.
`watermark`	No	Declared type: string.
`input_mode`	No	Declared type: string. Known values: "text", "first_and_last_frames", "reference".
`timeout_ms`	No
`aspect_ratio`	No	Declared type: string. Known values: "16:9", "9:16", "auto".
`callback_url`	No	Declared type: string.
`duration_seconds`	No	Declared type: integer. Known values: 4, 6, 8.
`poll_interval_ms`	No
`enable_translation`	No	Declared type: boolean.
`last_frame_image_url`	No	Declared type: string.
`reference_image_urls`	No	Declared type: array.
`first_frame_image_url`	No	Declared type: string.

Schema Changelog

Changes observed during successful MCP inspections.

Changed23 schema fields changedv0.2.0Oct 5, 2026
- changedInput schema / additionalProperties
```
Previous value: -falseNew value: +{}
```
- addedInput schema / properties / aspect_ratio / description
```
Added value: +"Declared type: string. Known values: \"16:9\", \"9:16\", \"auto\"."
```
- removedInput schema / properties / aspect_ratio / enum
```
Removed value: -[
-  "16:9",
-  "9:16",
-  "auto"
-]
```
- addedInput schema / properties / callback_url / description
```
Added value: +"Declared type: string."
```
- addedInput schema / properties / duration_seconds / description
```
Added value: +"Declared type: integer. Known values: 4, 6, 8."
```
- removedInput schema / properties / duration_seconds / enum
```
Removed value: -[
-  4,
-  6,
-  8
-]
```
- changedInput schema / properties / duration_seconds / type
```
Previous value: -"number"New value: +"integer"
```
- addedInput schema / properties / enable_translation / description
```
Added value: +"Declared type: boolean."
```
- addedInput schema / properties / first_frame_image_url / description
```
Added value: +"Declared type: string."
```
- addedInput schema / properties / input_mode / description
```
Added value: +"Declared type: string. Known values: \"text\", \"first_and_last_frames\", \"reference\"."
```
- removedInput schema / properties / input_mode / enum
```
Removed value: -[
-  "text",
-  "first_and_last_frames",
-  "reference"
-]
```
- addedInput schema / properties / last_frame_image_url / description
```
Added value: +"Declared type: string."
```
- removedInput schema / properties / model / enum
```
Removed value: -[
-  "veo-3.1",
-  "veo-3.1-fast",
-  "veo-3.1-lite"
-]
```
- addedInput schema / properties / poll_interval_ms / maximum
```
Added value: +9007199254740991
```
- addedInput schema / properties / prompt / description
```
Added value: +"Declared type: string."
```
- addedInput schema / properties / reference_image_urls / description
```
Added value: +"Declared type: array."
```
- removedInput schema / properties / reference_image_urls / maxItems
```
Removed value: -3
```
- removedInput schema / properties / reference_image_urls / minItems
```
Removed value: -1
```
- addedInput schema / properties / seeds / description
```
Added value: +"Declared type: integer."
```
- changedInput schema / properties / seeds / type
```
Previous value: -"number"New value: +"integer"
```
- addedInput schema / properties / timeout_ms / maximum
```
Added value: +9007199254740991
```
- addedInput schema / properties / watermark / description
```
Added value: +"Declared type: string."
```
- addedInput schema / required
```
Added value: +[]
```
Addedv0.1.9Jul 24, 2026
Removedv0.1.7Jul 22, 2026
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, so the description carries the full burden. It does disclose the return shape (task id, status, output URLs) and implies an async task model, but says nothing about required inputs, cost, permissions, or the effect of wait/callback_url on execution.

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?

Two short sentences, front-loaded with the action and resource, and the return-value sentence is placed second. Nothing is wasted or padded.

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 15-parameter async generation tool with no annotations and no output schema, the description is thin. It covers the return values but omits how prompt/input_mode/first_frame_image_url interact, the meaning of wait vs callback_url, and any cost or timeout context.

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 87%, above the 80% threshold, so the schema already documents most parameters and the baseline of 3 applies. The description adds no parameter meaning whatsoever beyond naming no fields.

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?

States a specific verb (Create) and resource (Veo 3.1 task, text-to-video) plus the backing service (RunAPI). It is clearly distinguishable from upscale_video and extend_video by resource, though it never explicitly contrasts itself with them.

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?

No when-to-use or when-not-to-use guidance. It never explains how this differs from extend_video or upscale_video, nor when to leave wait=true versus polling get_task, so the agent must infer the routing.

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

Deploy Server