Resize a video to one or more standard resolutions
AI agents use resize-video to create or update resources in Mcp Ffmpeg — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Ffmpeg environment.
Resizing a video creates a new output file at different resolutions. This is a Write operation as it produces new/modified data. It does not delete or overwrite the original source, and it does not execute arbitrary code or commands beyond the predefined resize operation. Severity is medium because misuse could produce unwanted files or consume significant disk/CPU resources.
From the tool's definition 'Resize a video to one or more standard resolutions' — modifies/transforms video output, but the original is typically preserved as a new file is created
Attacks that exploit this kind of access
Resize a video to one or more standard resolutions. It is categorised as a Write tool in the Mcp Ffmpeg MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Ffmpeg 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 Mcp Ffmpeg. 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 Mcp Ffmpeg MCP server (mcp-ffmpeg). 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 →