AI agents call check_autonomy 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.
This tool performs a permission check—it reads authorization status to determine if autonomous execution is allowed. It has no side effects on the 3D printer, materials, or any system state. While the information it returns may inform downstream decisions, the tool itself is purely informational/read-only.
From the tool's definition Tool name 'check_autonomy' and description 'Check whether the agent may execute a tool without human confirmation' indicates a query operation that retrieves or checks permission/authorization state without modifying any printer state, configuration, or data.
Attacks that exploit this kind of access
Check whether the agent may execute a tool without human confirmation. 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_autonomy: 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_autonomy 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_autonomy 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_autonomy. 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_autonomy 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 →