logs

What logs does on Http

AI agents call logs to retrieve information from Http without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Why logs is rated Low

The tool retrieves existing log data without side effects. It performs a passive read operation similar to fetching or querying information. While logs may contain sensitive information, the tool itself only reads data rather than modifying, executing, or destroying it. Severity is low because the blast radius of retrieving logs is limited to information disclosure, not operational impact.

From the tool's definition Tool name 'logs' and description 'Retrieves container logs as structured line arrays' indicate a query-only operation with no modification or execution capabilities.

The rule that runs logs safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Http, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For logs, this is the rule to start with:

{
  "version": "1",
  "default": "deny",
  "tools": {
    "logs": {}
  }
}

Questions about logs