pilotgentic_start_transcription

WHAT IT DOES

What pilotgentic_start_transcription does on PilotGentic

AI agents invoke pilotgentic_start_transcription to trigger actions in PilotGentic. 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 pilotgentic_start_transcription needs a policy

This tool executes an external transcription service (whisper-cli) and triggers system-level audio capture, making side effects observable but not immediately destructive or financial.

From the tool's definition 'Start system audio capture and Whisper transcription' — initiates external audio processing pipeline; 'transcribes via whisper-cli' — invokes external command-line tool; effects depend on what audio is being captured and how downstream tools use the…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

pilotgentic_start_transcription Rate-limited

pilotgentic_start_transcription 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": {
    "pilotgentic_start_transcription": {
      "limits": [
        {
          "counter": "pilotgentic_start_transcription_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 PilotGentic, so you can run agents against it safely.

FAQ

Questions about pilotgentic_start_transcription

What does the pilotgentic_start_transcription tool do? +

Start system audio capture and Whisper transcription. Buffers 10-second audio chunks, transcribes via whisper-cli, and appends timestamped text to /tmp/pilotgentic_transcript.txt. Read results with pilotgentic_read_transcript. It is categorised as a Execute tool in the PilotGentic MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on pilotgentic_start_transcription? +

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

What risk level is pilotgentic_start_transcription? +

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

Can I rate-limit pilotgentic_start_transcription? +

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

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

pilotgentic_start_transcription is provided by the PilotGentic MCP server (@pilotgentic/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.