AI agents call guardian_log to retrieve information from Cartridge without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves watchdog event log data for inspection purposes. The verb 'Get' and the nature of event logs (immutable historical records) indicate a read-only query with no ability to modify, delete, or execute operations. Even if an agent misuses this tool, it can only access log information without causing harm beyond potential information disclosure, which is a low-severity concern.
From the tool's definition Tool name contains 'log' and description states 'Get watchdog event log' — a retrieval operation with no side effects.
Attacks that exploit this kind of access
Get watchdog event log. It is categorised as a Read tool in the Cartridge MCP Server, which means it retrieves data without modifying state.
Register the Cartridge MCP server in PolicyLayer and add a rule for guardian_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 Cartridge. Nothing to install.
guardian_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 guardian_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 guardian_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.
guardian_log is provided by the Cartridge MCP server (lucineer/cartridge-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 →