Query Google Cloud Logs with custom filters. Searches across all payload types (text, JSON, proto) and metadata fields.
AI agents call gcp-logging-query-logs to retrieve information from GCP Billing and Monitoring MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and searches log data without side effects. It is categorized as Read because it performs queries and searches. However, severity is elevated to medium rather than low because: (1) logs may contain sensitive information including credentials, API keys, personally identifiable information (PII), or proprietary business logic; (2) an AI agent with unconstrained filter capabilities could exfiltrate…
From the tool's definition Tool performs 'Query Google Cloud Logs with custom filters' - a retrieval operation that searches logs without modifying or deleting them. The verb 'query' and 'searches' indicate read-only data access.
Attacks that exploit this kind of access
Query Google Cloud Logs with custom filters. Searches across all payload types (text, JSON, proto) and metadata fields. It is categorised as a Read tool in the GCP Billing and Monitoring MCP Server MCP Server, which means it retrieves data without modifying state.
Register the GCP Billing and Monitoring MCP Server MCP server in PolicyLayer and add a rule for gcp-logging-query-logs: 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 GCP Billing and Monitoring MCP Server. Nothing to install.
gcp-logging-query-logs 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-logging-query-logs 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-logging-query-logs. 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-logging-query-logs is provided by the GCP Billing and Monitoring MCP Server MCP server (radiumgu/gcp-billing-and-monitoring-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 →