AI agents call gsc_inspect_url 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.
URL inspection in Google Search Console returns information about a URL's indexing status, mobile usability, and other metadata—a read operation with no side effects. The broader server context confirms read-only access. Severity is low because inspection cannot modify data or trigger external operations; blast radius is limited to information disclosure.
From the tool's definition Server description states 'read-only tools' and lists 'URL inspection' as a capability. Tool name 'gsc_inspect_url' aligns with inspection (querying data) rather than modification. No description provided for the tool itself, which slightly lowers confidence.
Attacks that exploit this kind of access
gsc_inspect_url. 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_inspect_url: 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_inspect_url 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_inspect_url 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_inspect_url. 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_inspect_url 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 →