POST /api/v1/transcripts/bulk-delete. Delete transcripts by ids or by video_id.
AI agents call delete_transcript to permanently remove resources in Youtube Transcript — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly removes data (transcripts) from the system. Deletion is the canonical Destructive operation—it cannot be undone and results in permanent data loss. The 'bulk-delete' capability amplifies the blast radius, as a single call could remove multiple transcripts.
From the tool's definition Tool is named 'delete_transcript' and explicitly performs deletion via 'bulk-delete' endpoint. Description states 'Delete transcripts by ids or by video_id' with no recovery mechanism described.
Attacks that exploit this kind of access
POST /api/v1/transcripts/bulk-delete. Delete transcripts by ids or by video_id. It is categorised as a Destructive tool in the Youtube Transcript MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Youtube Transcript MCP server in PolicyLayer and add a rule for delete_transcript: 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 Youtube Transcript. Nothing to install.
delete_transcript 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 delete_transcript 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 delete_transcript. 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.
delete_transcript is provided by the Youtube Transcript MCP server (youtube-transcript-dev/youtube-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 →