transcribe_file · Whipscribe MCP: Risk & Policy

WHAT IT DOES

What transcribe_file does on Whipscribe

AI agents invoke transcribe_file to trigger actions in Whipscribe. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why transcribe_file needs a policy

This tool takes a local file path and submits it to a transcription service, constituting an external operation triggered by arguments. It accesses local filesystem resources and invokes processing. The description is cut off, lowering confidence. The most severe applicable category is Execute since it triggers an external operation. Misuse could expose sensitive local audio/video files to the transcription service.

From the tool's definition 'Transcribe a local audio or video file. The path is never' — description is truncated/incomplete, but the tool reads a local file path and triggers an external transcription operation

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

transcribe_file Rate-limited

transcribe_file stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "transcribe_file": {
      "limits": [
        {
          "counter": "transcribe_file_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

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

FAQ

Questions about transcribe_file

What does the transcribe_file tool do? +

Transcribe a local audio or video file. The path is never. It is categorised as a Execute tool in the Whipscribe MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on transcribe_file? +

Register the Whipscribe MCP server in PolicyLayer and add a rule for transcribe_file: 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 Whipscribe. Nothing to install.

What risk level is transcribe_file? +

transcribe_file is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit transcribe_file? +

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

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

transcribe_file is provided by the Whipscribe MCP server (neugence/whipscribe-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.