Critical Risk →

transcribe_delete

Soft-delete a Scriptivox transcription record. Idempotent. Returns 409 CONFLICT if the job is still in-flight — cancel first via transcribe_cancel. Requires a configured API key.

How to control transcribe_delete ↓

What transcribe_delete does on Scriptivox

AI agents call transcribe_delete to permanently remove resources in Scriptivox — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.

Critical Risk

Why transcribe_delete needs a policy

Although described as 'soft-delete' (which typically means logical deletion rather than physical erasure), the tool irreversibly removes access to transcription data from the user's perspective and cannot be undone via this tool's API. The action results in permanent loss of the transcription record. This qualifies as Destructive rather than Write because deletion is not reversible.

From the tool's definition Soft-delete a Scriptivox transcription record. The verb 'delete' combined with the irreversible removal of data (transcription records) matches the Destructive category definition.

Documented attack patterns abuse exactly the kind of access transcribe_delete gives an agent:

How to control transcribe_delete

PolicyLayer is an MCP gateway — it sits between your AI agents and Scriptivox, and nothing reaches the server without passing your rules. This is the rule we recommend for transcribe_delete:

policy.json
{
  "version": "1",
  "default": "deny",
  "hide": [
    "transcribe_delete"
  ]
}

transcribe_delete disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.

  1. Create a free account and register Scriptivox — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
RESTRICT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about transcribe_delete

What does the transcribe_delete tool do? +

Soft-delete a Scriptivox transcription record. Idempotent. Returns 409 CONFLICT if the job is still in-flight — cancel first via transcribe_cancel. Requires a configured API key. It is categorised as a Destructive tool in the Scriptivox MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.

How do I enforce a policy on transcribe_delete? +

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

What risk level is transcribe_delete? +

transcribe_delete is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.

Can I rate-limit transcribe_delete? +

Yes. Add a rate_limit block to the transcribe_delete 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_delete completely? +

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

transcribe_delete is provided by the Scriptivox MCP server (oci:docker.io/sparkleofficialmain/scriptivox-mcp-server:1.1.3). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Scriptivox tool call.

Start from Scriptivox, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

Free to start. No card required.

14 Scriptivox tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.