AI agents call gsc.sites.list to retrieve information from Ads without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a simple query/list operation to retrieve metadata about sites already configured in Google Search Console. It retrieves data without modifying, deleting, or executing any operations. The only permission required is read access to the authenticated account's site list. Blast radius is minimal as it only exposes configuration metadata.
From the tool's definition Tool name 'gsc.sites.list' and description 'List sites verified for the authenticated account' indicate a retrieval operation with no side effects.
Attacks that exploit this kind of access
List sites verified for the authenticated account. It is categorised as a Read tool in the Ads MCP Server, which means it retrieves data without modifying state.
Register the Ads MCP server in PolicyLayer and add a rule for gsc.sites.list: 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.list is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the gsc.sites.list 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.list. 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.list 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 →