Cancel an async transcription job (best-effort).
AI agents call transcribe_cancel_job to permanently remove resources in Video Toolkit — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Cancelling an async job is an irreversible action — once cancelled, the in-progress transcription job cannot be resumed. This matches the Destructive category as it permanently terminates an ongoing operation. Severity is medium since it only affects a single transcription job rather than persistent data, but the work done so far would be lost.
From the tool's definition Cancel an async transcription job (best-effort)
Attacks that exploit this kind of access
Cancel an async transcription job (best-effort). It is categorised as a Destructive tool in the Video Toolkit MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Video Toolkit MCP server in PolicyLayer and add a rule for transcribe_cancel_job: 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 Video Toolkit. Nothing to install.
transcribe_cancel_job is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the transcribe_cancel_job 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.
Set action: deny in the PolicyLayer policy for transcribe_cancel_job. 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.
transcribe_cancel_job is provided by the Video Toolkit MCP server (jamesanz/transcript-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →