AI agents invoke runway_generate_video to trigger actions in UnClick. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
| Parameter | Type | Required | Description |
|---|---|---|---|
seed | number | — | Random seed for reproducibility |
model | string | — | Model name: gen3a_turbo (fast) or gen3a (quality). Default: gen3a_turbo |
ratio | string | — | Aspect ratio e.g. 1280:768 or 768:1280 (default: 1280:768) |
prompt | string | — | Text description of the video to generate |
api_key | string | Yes | Runway API key |
duration | number | — | Video duration in seconds (default: 5) |
image_url | string | — | URL of an image to animate (image-to-video mode) |
Parameters from the server's own tool schema.
This tool triggers an external AI video generation service (Runway ML), which constitutes an external operation execution. It is not a simple read/write — it initiates a compute-intensive external task and returns a task_id for polling. Misuse could result in significant API costs (approaching Financial) and generation of harmful video content, justifying high severity.
From the tool's definition Generate a video from text or an image using Runway ML... triggers external operations (video generation via Runway ML API)
Risk signalsHandles credentials or secrets (api_key)
Attacks that exploit this kind of access
Generate a video from text or an image using Runway ML. Supports text-to-video and image-to-video. Returns a task_id to poll for completion. It is categorised as a Execute tool in the UnClick MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
runway_generate_video accepts 7 parameters: seed, model, ratio, prompt, api_key, duration, image_url. Required: api_key. The full parameter table on this page comes from the server's own tool schema.
Register the UnClick MCP server in PolicyLayer and add a rule for runway_generate_video: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches UnClick. Nothing to install.
runway_generate_video is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the runway_generate_video rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for runway_generate_video. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
runway_generate_video is provided by the UnClick MCP server (@unclick/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →