watermark · Ffmpeg MCP: Risk & Policy

WHAT IT DOES

What watermark does on Ffmpeg

AI agents use watermark 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.

WHY IT NEEDS A POLICY

Why watermark needs a policy

The watermark tool modifies video data by adding visual overlays with configurable position and opacity. While this changes the video file, it is reversible through re-processing or editing. The severity is medium because misuse could deface or alter legitimate content, but the effects are not destructive (original file is not overwritten in-place) and not irreversible.

From the tool's definition Tool description: 'Add image or text watermark to video.' The verb 'Add' indicates creation/modification of video content. This modifies the video file by overlaying a watermark, which is a reversible edit (watermark can be removed or replaced).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

watermark Rate-limited

watermark 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "watermark": {
      "limits": [
        {
          "counter": "watermark_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Ffmpeg, so you can run agents against it safely.

FAQ

Questions about watermark

What does the watermark tool do? +

Add image or text watermark to video. Supports position control (corners/center) and opacity. 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.

How do I enforce a policy on watermark? +

Register the Ffmpeg MCP server in PolicyLayer and add a rule for watermark: 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.

What risk level is watermark? +

watermark is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit watermark? +

Yes. Add a rate_limit block to the watermark 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.

How do I block watermark completely? +

Set action: deny in the PolicyLayer policy for watermark. 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.

What MCP server provides watermark? +

watermark 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.