调整视频尺寸
AI agents use resize_video to create or update resources in FFmpeg MCP Tool — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your FFmpeg MCP Tool environment.
Resizing a video creates or overwrites a modified version of the file. This is a Write operation as it modifies media data. It is not Destructive because the original is typically preserved, not irreversibly deleted. Severity is medium because misuse could overwrite important video files or produce unintended output dimensions, but the blast radius is limited to media files.
From the tool's definition Tool name 'resize_video' and description '调整视频尺寸' (meaning 'adjust video dimensions/size') indicate a transformation/modification operation on video files.
Attacks that exploit this kind of access
调整视频尺寸. It is categorised as a Write tool in the FFmpeg MCP Tool MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the FFmpeg MCP Tool MCP server in PolicyLayer and add a rule for resize_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 Tool. Nothing to install.
resize_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 resize_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 resize_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.
resize_video is provided by the FFmpeg MCP Tool MCP server (lbjwt/ffmpeg-mcp). 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 →