视频缩放 参数： width(int) - 目标宽度。 height(int) - 目标高度。 output_path(str) - 输出路径
AI agents use scale_video to create or update resources in FFmpeg-MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your FFmpeg-MCP Server environment.
This tool transforms a video by resizing it and writes the result to a new output file. It creates/modifies data reversibly (the original is not destroyed, a new file is produced), placing it in the Write category. Misuse could overwrite existing files if the output path matches an existing file, but no indication of irreversible deletion of source material.
From the tool's definition 视频缩放 (video scaling) with parameters for width, height, and output_path — creates a new scaled video file at the specified output path
Documented attack patterns abuse exactly the kind of access scale_video gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and FFmpeg-MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for scale_video:
{
"version": "1",
"default": "deny",
"tools": {
"scale_video": {
"limits": [
{
"counter": "scale_video_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}scale_video stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
视频缩放 参数： width(int) - 目标宽度。 height(int) - 目标高度。 output_path(str) - 输出路径. It is categorised as a Write tool in the FFmpeg-MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the FFmpeg-MCP Server MCP server in PolicyLayer and add a rule for scale_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 FFmpeg-MCP Server. Nothing to install.
scale_video is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the scale_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 scale_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.
scale_video is provided by the FFmpeg-MCP Server MCP server (video-creator/ffmpeg-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 8 FFmpeg-MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
8 FFmpeg-MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.