add_audio · Ffmpeg MCP: Risk & Policy

WHAT IT DOES

What add_audio does on Ffmpeg

AI agents use add_audio 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 add_audio needs a policy

This tool modifies video files by adding or replacing audio tracks. While the changes are non-destructive in the sense that the original file is not deleted and the operation can be undone or corrected (e.g., by re-processing or using version control), it does alter media files. It falls into the Write category as it creates or modifies data reversibly.

From the tool's definition Tool description states 'Add or replace audio track in video' and 'Mix with original audio or replace entirely' — these are reversible modifications to video files.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

add_audio Rate-limited

add_audio 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": {
    "add_audio": {
      "limits": [
        {
          "counter": "add_audio_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 add_audio

What does the add_audio tool do? +

Add or replace audio track in video. Mix with original audio or replace entirely. 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 add_audio? +

Register the Ffmpeg MCP server in PolicyLayer and add a rule for add_audio: 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 add_audio? +

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

Can I rate-limit add_audio? +

Yes. Add a rate_limit block to the add_audio 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 add_audio completely? +

Set action: deny in the PolicyLayer policy for add_audio. 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 add_audio? +

add_audio 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.