Generate a video from an image using Kling AI
AI agents invoke generate_image_to_video to trigger actions in MCP Kling. 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.
This tool triggers an external AI video generation operation using Kling AI's services, consuming computational resources and potentially API credits. It executes an external process whose effects depend on the input image and parameters. It's not purely destructive or financial, but it does trigger a real external operation beyond simple data writes.
From the tool's definition Generate a video from an image using Kling AI
Documented attack patterns abuse exactly the kind of access generate_image_to_video gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Kling, and nothing reaches the server without passing your rules. This is the rule we recommend for generate_image_to_video:
{
"version": "1",
"default": "deny",
"tools": {
"generate_image_to_video": {
"limits": [
{
"counter": "generate_image_to_video_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
} generate_image_to_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.
Free to start. No card required.
Generate a video from an image using Kling AI. It is categorised as a Execute tool in the MCP Kling MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP Kling MCP server in PolicyLayer and add a rule for generate_image_to_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 MCP Kling. Nothing to install.
generate_image_to_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 generate_image_to_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 generate_image_to_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.
generate_image_to_video is provided by the MCP Kling MCP server (199-mcp/mcp-kling). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP Kling, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
12 MCP Kling tools catalogued and risk-classified — across an index of 43,000+ MCP servers.