AI agents invoke kling_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 |
|---|---|---|---|
mode | string | — | Generation mode: std (standard) or pro (professional, slower). Default: std |
model | string | — | Model name: kling-v1 or kling-v1-5 (default: kling-v1) |
prompt | string | Yes | Text description of the video to generate |
api_key | string | Yes | Kling AI API key |
duration | string | — | Video duration: 5 or 10 (seconds). Default: 5 |
cfg_scale | number | — | Guidance scale 0-1 (default: 0.5) |
image_url | string | — | Optional reference image URL for image-to-video |
aspect_ratio | string | — | e.g. 16:9, 9:16, 1:1. Default: 16:9 |
negative_prompt | string | — | What to avoid in the video |
Parameters from the server's own tool schema.
This tool triggers an external AI video generation operation on a third-party service (Kling AI/Kuaishou). It initiates an asynchronous external process with real-world side effects (API calls, compute consumption, potential costs). It is best classified as Execute since it runs an external operation whose effects depend on the input arguments.
From the tool's definition Generate a high-quality video from text using Kling AI (Kuaishou)... Returns a task_id to poll for completion.
Risk signalsHandles credentials or secrets (api_key)
Attacks that exploit this kind of access
Generate a high-quality video from text using Kling AI (Kuaishou). Supports standard and professional modes. 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.
kling_generate_video accepts 9 parameters: mode, model, prompt, api_key, duration, cfg_scale, image_url, aspect_ratio, negative_prompt. Required: prompt, 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 kling_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.
kling_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 kling_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 kling_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.
kling_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 →