AI agents call get_autonomy_level 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 queries and returns configuration or state information about autonomy settings. There are no side effects, data modifications, code execution, deletions, or financial implications. It is purely informational—equivalent to a GET request in REST terminology. Low severity because reading autonomy constraints poses minimal risk even if misused by an agent; the information cannot directly harm hardware or data.
From the tool's definition Tool name 'get_autonomy_level' and description 'Return the current autonomy tier and constraints' indicate a query operation that retrieves system state without modification.
Attacks that exploit this kind of access
Return the current autonomy tier and constraints. 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 get_autonomy_level: 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.
get_autonomy_level 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 get_autonomy_level 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 get_autonomy_level. 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.
get_autonomy_level 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 →