generate_narration · Hyper Video Service MCP: Risk & Policy

WHAT IT DOES

What generate_narration does on Hyper Video Service

AI agents use generate_narration to create or update resources in Hyper Video Service — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Hyper Video Service environment.

WHY IT NEEDS A POLICY

Why generate_narration needs a policy

This tool creates/modifies data (adds narration audio to a video) in a reversible manner. It does not execute arbitrary code, delete data, or move money. While it involves external API calls to ElevenLabs, the primary operation is data modification rather than code execution.

From the tool's definition Tool description states it will 'Generate narration audio from text using ElevenLabs text-to-speech, then mux it onto an existing video' and 'Returns the updated video download URL when done.' The action modifies an existing video by adding audio content to…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

generate_narration Rate-limited

generate_narration 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": {
    "generate_narration": {
      "limits": [
        {
          "counter": "generate_narration_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 Hyper Video Service, so you can run agents against it safely.

FAQ

Questions about generate_narration

What does the generate_narration tool do? +

Generate narration audio from text using ElevenLabs text-to-speech, then mux it onto an existing video. Returns the updated video download URL when done. Available voices:. It is categorised as a Write tool in the Hyper Video Service MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on generate_narration? +

Register the Hyper Video Service MCP server in PolicyLayer and add a rule for generate_narration: 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 Hyper Video Service. Nothing to install.

What risk level is generate_narration? +

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

Can I rate-limit generate_narration? +

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

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

generate_narration is provided by the Hyper Video Service MCP server (twilson63/hyper-video-service). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.