AI agents call gsc_top_pages to retrieve information from Gsc without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries search analytics data without side effects. It is a passive read operation that returns metrics over a historical period. The server is explicitly documented as 'read-only' and provides no capability to modify, delete, or execute external operations. Misuse would be limited to unauthorized access to analytics data, a lower-severity breach compared to write/execute/destructive actions.
From the tool's definition Tool returns aggregated analytics data (top landing pages) for a site; described as 'read-only' in server description; no parameters or actions that modify, delete, or execute operations.
Attacks that exploit this kind of access
Return the top N landing pages for a site over a recent period. It is categorised as a Read tool in the Gsc MCP Server, which means it retrieves data without modifying state.
Register the Gsc MCP server in PolicyLayer and add a rule for gsc_top_pages: 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 Gsc. Nothing to install.
gsc_top_pages 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_top_pages 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_top_pages. 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_top_pages is provided by the Gsc MCP server (jayrockliffe-defused/gsc-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 →