gcp-monitoring-query-metrics
AI agents call gcp-monitoring-query-metrics to retrieve information from Google Cloud MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool queries metrics data from Cloud Monitoring, which is a read operation. However, depending on what metrics are exposed (e.g., sensitive infrastructure details, security events, cost data), the blast radius if an AI misuses this could be moderate—hence medium severity rather than low.
From the tool's definition Tool name 'gcp-monitoring-query-metrics' indicates querying Cloud Monitoring metrics. The server description states it allows users to 'analyze Cloud Monitoring metrics through natural language interaction.' Query operations are read-only with no side effects.
Documented attack patterns abuse exactly the kind of access gcp-monitoring-query-metrics gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Google Cloud MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for gcp-monitoring-query-metrics:
{
"version": "1",
"default": "deny",
"tools": {
"gcp-monitoring-query-metrics": {}
}
} gcp-monitoring-query-metrics is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
gcp-monitoring-query-metrics. It is categorised as a Read tool in the Google Cloud MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Google Cloud MCP Server MCP server in PolicyLayer and add a rule for gcp-monitoring-query-metrics: 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 Google Cloud MCP Server. Nothing to install.
gcp-monitoring-query-metrics 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 gcp-monitoring-query-metrics 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 gcp-monitoring-query-metrics. 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.
gcp-monitoring-query-metrics is provided by the Google Cloud MCP Server MCP server (krzko/google-cloud-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Google Cloud MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
40 Google Cloud MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.