gen_video
Async text-to-video via FAL (Kling/Veo). BYOK ONLY. Returns {ok, job_id} — the generation runs off your context (1-5 min); poll check_errand for the video URL.
This record as markdown: /tools/com-wingmanprotocol-agent-gateway/gen-video.md
What gen_video does on Gateway
AI agents invoke gen_video to trigger actions in Gateway. 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 |
|---|---|---|---|
model | string | — | fal-ai/kling-video/... (default) | veo3/fast | wan/v2.2/1080p |
handle | string | — | your handle (for BYOK via vault) |
prompt | string | Yes | what to generate |
secret | string | — | your agent secret (for BYOK via vault) |
api_key | string | — | your FAL key (BYOK, inline) |
key_ref | string | — | vault entry holding your FAL key (BYOK alt) |
duration | string | — | seconds, e.g. '5' (model-dependent) |
aspect_ratio | string | — | e.g. 16:9 (default) | 9:16 | 1:1 |
Parameters from the server's own tool schema.
Why gen_video is rated High
This tool triggers an external video generation operation via a third-party AI service (FAL/Kling/Veo). It executes an asynchronous job whose effects (API calls, compute consumption, potential costs under BYOK) depend on the arguments provided. It doesn't merely read or write local data — it initiates an external process.
From the tool's definition Async text-to-video via FAL (Kling/Veo)... Returns {ok, job_id} — the generation runs off your context (1-5 min); poll check_errand for the video URL.
Risk signalsHandles credentials or secrets (api_key)
Attacks that exploit this kind of access
The rule that runs gen_video safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Gateway, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For gen_video, this is the rule to start with:
gen_video stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Gateway, apply this rule, and every gen_video call is checked against it from then on.
Questions about gen_video
Async text-to-video via FAL (Kling/Veo). BYOK ONLY. Returns {ok, job_id} — the generation runs off your context (1-5 min); poll check_errand for the video URL. It is categorised as a Execute tool in the Gateway MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
gen_video accepts 8 parameters: model, handle, prompt, secret, api_key, key_ref, duration, aspect_ratio. Required: prompt. The full parameter table on this page comes from the server's own tool schema.
Register the Gateway MCP server in PolicyLayer and add a rule for gen_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 Gateway. Nothing to install.
gen_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 gen_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 gen_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.
gen_video is provided by the Gateway MCP server (https://wingmanprotocol.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Gateway, and thousands of servers like it.
Across the catalogue