AI agents use gsc.sites.add to create or update resources in Ads — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Ads environment.
Adding/claiming a site in Google Search Console is a Write operation: it creates a new resource (site claim) in the system. It is reversible (sites can be removed). Misuse could result in unauthorized site claims under a managed account, giving medium severity.
From the tool's definition 'Claim a site in Search Console' — this creates/registers a new site entry, a reversible write action. 'Verification still required separately' confirms it does not fully activate or delete anything.
Attacks that exploit this kind of access
Claim a site in Search Console. Verification still required separately. It is categorised as a Write tool in the Ads MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Ads MCP server in PolicyLayer and add a rule for gsc.sites.add: 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.add is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the gsc.sites.add 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.add. 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.add 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 →