Check for recent security alerts and suspicious login attempts
AI agents call check_suspicious_activity to retrieve information from Google Workspace Compliance Audit Tool 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 security logs and alert data without creating, modifying, or deleting anything. It has no side effects beyond information disclosure. While the data accessed may be sensitive, the tool itself cannot cause damage or take actions based on findings. Severity is low because misuse results only in information exposure, not operational impact.
From the tool's definition Tool performs checking/querying of existing security alerts and login attempts without modification. Keywords: 'Check for recent' and 'suspicious login attempts' indicate retrieval of audit/security data.
Attacks that exploit this kind of access
Check for recent security alerts and suspicious login attempts. It is categorised as a Read tool in the Google Workspace Compliance Audit Tool MCP Server, which means it retrieves data without modifying state.
Register the Google Workspace Compliance Audit Tool MCP server in PolicyLayer and add a rule for check_suspicious_activity: 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 Workspace Compliance Audit Tool. Nothing to install.
check_suspicious_activity 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 check_suspicious_activity 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 check_suspicious_activity. 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.
check_suspicious_activity is provided by the Google Workspace Compliance Audit Tool MCP server (sean-m-sweeney/googleworkspaceaudit). 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 →