AI agents call gsc_health_check 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 is a health-check utility that queries the state of authentication and API connectivity. It retrieves status information without creating, modifying, deleting, or executing code. The server itself is explicitly described as 'read-only', and this tool fits that constraint.
From the tool's definition Tool performs a diagnostic check to validate OAuth token and API reachability. The description uses 'confirm' and 'diagnostic', indicating passive verification with no data modification or execution of external operations.
Attacks that exploit this kind of access
Diagnostic: confirm the OAuth token is valid and the Search Console API is reachable. 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_health_check: 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_health_check 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_health_check 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_health_check. 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_health_check 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 →