AI agents call check_print_health to retrieve information from Kiln without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The name indicates a diagnostic check that retrieves printer health metrics without modifying state or triggering operations. The absence of description lowers confidence slightly, but context from sibling tools (status, analyze functions) and naming convention suggest this is a passive monitoring operation. Categorized as Read due to lack of evidence of side effects.
From the tool's definition Tool name 'check_print_health' suggests monitoring/querying printer status; no description provided. Sibling tools include status queries (ams_status) and read-only operations (analyze_design_requirements, analyze_generation_feedback).
Attacks that exploit this kind of access
check_print_health. It is categorised as a Read tool in the Kiln MCP Server, which means it retrieves data without modifying state.
Register the Kiln MCP server in PolicyLayer and add a rule for check_print_health: 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 Kiln. Nothing to install.
check_print_health 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_print_health 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_print_health. 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_print_health is provided by the Kiln MCP server (codeofaxel/Kiln). 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 →