Unsubscribe (delete a subscription). Costs 50 quota units.
AI agents call unsubscribe to permanently remove resources in Youtube — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool explicitly deletes a subscription, which is an irreversible removal action. Once unsubscribed, the subscription relationship is destroyed and cannot be recovered without re-subscribing (a separate action). This maps to the Destructive category. Severity is medium as the blast radius is limited to subscription state rather than content or financial data.
From the tool's definition Unsubscribe (delete a subscription)
Attacks that exploit this kind of access
Unsubscribe (delete a subscription). Costs 50 quota units. It is categorised as a Destructive tool in the Youtube MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Youtube MCP server in PolicyLayer and add a rule for unsubscribe: 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. Nothing to install.
unsubscribe 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 unsubscribe 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 unsubscribe. 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.
unsubscribe is provided by the Youtube MCP server (kpfitzgerald/youtube-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 →