diarize_speech · Whissle MCP Server MCP: Risk & Policy

WHAT IT DOES

What diarize_speech does on Whissle MCP Server

AI agents invoke diarize_speech to trigger actions in Whissle MCP Server. 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 diarize_speech needs a policy

This tool triggers an external API operation (Whissle) to perform speaker diarization on audio input. It executes an external service call with side effects (API usage, processing), placing it in the Execute category. The blast radius is medium as misuse could lead to unauthorized API calls or processing of sensitive audio data, but it does not directly modify, delete, or involve financial transactions.

From the tool's definition Diarize speech using Whissle API

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

diarize_speech Rate-limited

diarize_speech 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": {
    "diarize_speech": {
      "limits": [
        {
          "counter": "diarize_speech_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 Whissle MCP Server, so you can run agents against it safely.

FAQ

Questions about diarize_speech

What does the diarize_speech tool do? +

Diarize speech using Whissle API. It is categorised as a Execute tool in the Whissle MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on diarize_speech? +

Register the Whissle MCP Server MCP server in PolicyLayer and add a rule for diarize_speech: 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 Whissle MCP Server. Nothing to install.

What risk level is diarize_speech? +

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

Can I rate-limit diarize_speech? +

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

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

diarize_speech is provided by the Whissle MCP Server MCP server (whissleai/whissle-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.