AI agents call get_cached_model 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 retrieves cached model information without side effects. It is a read-only query operation on previously stored data. The low severity reflects minimal risk — even if an agent retrieves unauthorized cached models, the blast radius is limited to information disclosure, not physical printer control, data deletion, or financial impact.
From the tool's definition Tool name 'get_cached_model' combined with description 'Return details for a specific cached model' indicates a retrieval operation with no modification or execution of external systems.
Attacks that exploit this kind of access
Return details for a specific cached model. 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_cached_model: 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_cached_model 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_cached_model 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_cached_model. 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_cached_model 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 →