Unclaim a site in Search Console. High-risk; dry-run by default.
AI agents call gsc.sites.delete to permanently remove resources in Ads — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Unclaiming a site in Search Console removes the association between the user and that property, which can result in loss of access to all historical search performance data and settings. This action is not easily reversible (re-adding and re-verifying a site is a manual process and data continuity may be affected). The tool's own description acknowledges it is high-risk, placing it firmly in the Destructive category.
From the tool's definition 'Unclaim a site in Search Console. High-risk; dry-run by default.' — 'unclaim' is an irreversible removal of site ownership/access, and the description itself flags it as 'High-risk'.
Attacks that exploit this kind of access
Unclaim a site in Search Console. High-risk; dry-run by default. It is categorised as a Destructive tool in the Ads MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Ads MCP server in PolicyLayer and add a rule for gsc.sites.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 Ads. Nothing to install.
gsc.sites.delete 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 gsc.sites.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.
Set action: deny in the PolicyLayer policy for gsc.sites.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.
gsc.sites.delete is provided by the Ads MCP server (manlikemuneeb/ads-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 →