AI agents call guardian_status 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 is a read-only operation that retrieves status information about monitored systems ('vessels'). It has no side effects, does not execute code, does not modify data, and does not involve financial transactions. The blast radius of misuse is minimal—an agent could only gain visibility into system health metrics, which does not compromise data integrity or trigger unwanted operations.
From the tool's definition Tool name 'guardian_status' and description 'Get fleet health overview — all monitored vessels' indicate a query operation that retrieves monitoring/health data without modifying state or triggering external actions.
Attacks that exploit this kind of access
Get fleet health overview — all monitored vessels. 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_status: 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_status 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_status 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_status. 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_status 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 →