AI agents call ams_status 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.
Status queries are non-destructive reads that retrieve printer state information. Given the context of 3D printer control and the '_status' naming convention, this tool almost certainly retrieves state without side effects. The empty description lowers confidence slightly, but the tool name and context strongly indicate a Read classification with low severity impact.
From the tool's definition Tool name 'ams_status' suggests querying status of an AMS (Filament Management System) component common in 3D printers like Bambu; the empty description prevents full certainty, but the naming pattern '_status' consistently indicates read-only monitoring…
Attacks that exploit this kind of access
ams_status. 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 ams_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 Kiln. Nothing to install.
ams_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 ams_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 ams_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.
ams_status 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 →