AI agents use resize to create or update resources in Ffmpeg — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Ffmpeg environment.
The resize tool modifies a video file by changing its resolution/scale. This is a Write operation as it creates or modifies data (the video file). While it overwrites the file, video processing tools typically write to a new output file rather than destructively modifying the original in place, making Write the most appropriate category. The blast radius is medium as it could affect important media files.
From the tool's definition Change video resolution/scale. Specify width and height (-1 for auto aspect ratio).
Attacks that exploit this kind of access
Change video resolution/scale. Specify width and height (-1 for auto aspect ratio). It is categorised as a Write tool in the Ffmpeg MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Ffmpeg MCP server in PolicyLayer and add a rule for resize: 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. Nothing to install.
resize 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 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. 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 is provided by the Ffmpeg MCP server (yuan66-hub/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 →