openai_create_transcription · UnClick MCP: Risk & Policy

WHAT IT DOES

What openai_create_transcription does on UnClick

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

PARAMETERS

Parameter	Type	Required	Description
`model`	string	—	Transcription model (default: whisper-1)
`prompt`	string	—
`api_key`	string	Yes
`filename`	string	—
`language`	string	—	ISO-639-1 language code (optional)
`audio_url`	string	Yes	URL of the audio file to transcribe
`temperature`	number	—
`response_format`	string	—	json, text, srt, verbose_json, vtt (default: json)

Parameters from the server's own tool schema.

WHY IT NEEDS A POLICY

Why openai_create_transcription needs a policy

An AI agent can call openai_create_transcription faster than any human can review — one bad instruction and it creates or modifies resources in UnClick by the hundred, each call as confident as the last.

Risk signalsAccepts file system path (filename) · Handles credentials or secrets (api_key)

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

openai_create_transcription Rate-limited

openai_create_transcription 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": {
    "openai_create_transcription": {
      "limits": [
        {
          "counter": "openai_create_transcription_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 UnClick, so you can run agents against it safely.

FAQ

Questions about openai_create_transcription

What does the openai_create_transcription tool do? +

Transcribe audio to text using OpenAI Whisper. It is categorised as a Write tool in the UnClick MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

What parameters does openai_create_transcription accept? +

openai_create_transcription accepts 8 parameters: model, prompt, api_key, filename, language, audio_url, temperature, response_format. Required: api_key, audio_url. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on openai_create_transcription? +

Register the UnClick MCP server in PolicyLayer and add a rule for openai_create_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 UnClick. Nothing to install.

What risk level is openai_create_transcription? +

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

Can I rate-limit openai_create_transcription? +

Yes. Add a rate_limit block to the openai_create_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 openai_create_transcription completely? +

Set action: deny in the PolicyLayer policy for openai_create_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 openai_create_transcription? +

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