Retrieve system log entries for debugging or auditing
AI agents call get_sys_log to retrieve information from ServiceNow-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves existing system log data without creating, modifying, or deleting information. It presents no destructive risk and no side effects beyond querying. While logs may contain sensitive information, the tool itself is a passive read operation. Severity is low because log retrieval alone does not enable code execution, financial transactions, or data destruction.
From the tool's definition Tool name 'get_sys_log' and description 'Retrieve system log entries for debugging or auditing' indicate data retrieval without modification.
Attacks that exploit this kind of access
Retrieve system log entries for debugging or auditing. It is categorised as a Read tool in the ServiceNow-MCP MCP Server, which means it retrieves data without modifying state.
Register the ServiceNow- MCP server in PolicyLayer and add a rule for get_sys_log: 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 ServiceNow-MCP. Nothing to install.
get_sys_log 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 get_sys_log 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 get_sys_log. 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.
get_sys_log is provided by the ServiceNow- MCP server (tedorigawa001/servicenow-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 →