Query Google Cloud logs using the powerful Cloud Logging filter syntax. FILTER SYNTAX: - Operators: = != > >= < <= : (contains) =~ (regex match) !~ (regex not match) - Boolean: AND OR NOT and parentheses () - Common fields: severity, timestamp, resource.type, resource.labels.*, textPayload, jsonP...
AI agents call queryLogs to retrieve information from Google Cloud Logging 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 queries log data without modifying, deleting, or executing operations. It falls under the Read category. Severity is medium rather than low because logs can contain sensitive information (credentials, personal data, internal architecture details), and an AI agent with broad log access could exfiltrate sensitive data from Cloud projects, though the blast radius is limited to information…
From the tool's definition Tool description states it 'Query Google Cloud logs' and 'retrieves...log entry'. The filter syntax documentation describes query operations (=, !=, >, >=, <, <=, :, =~, !~) for filtering and searching logs, with no modification, deletion, or execution…
Documented attack patterns abuse exactly the kind of access queryLogs gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Google Cloud Logging MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for queryLogs:
{
"version": "1",
"default": "deny",
"tools": {
"queryLogs": {}
}
}queryLogs 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.
Query Google Cloud logs using the powerful Cloud Logging filter syntax. FILTER SYNTAX: - Operators: = != > >= < <= : (contains) =~ (regex match) !~ (regex not match) - Boolean: AND OR NOT and parentheses () - Common fields: severity, timestamp, resource.type, resource.labels.*, textPayload, jsonPayload.*, labels.*, logName SEARCH FUNCTION: Use SEARCH(. It is categorised as a Read tool in the Google Cloud Logging MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Google Cloud Logging MCP Server MCP server in PolicyLayer and add a rule for queryLogs: 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 Logging MCP Server. Nothing to install.
queryLogs 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 queryLogs 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 queryLogs. 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.
queryLogs is provided by the Google Cloud Logging MCP Server MCP server (swen128/cloud-logging-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Google Cloud Logging 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.
3 Google Cloud Logging MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.