cache_model · Kiln MCP: Risk & Policy

WHAT IT DOES

What cache_model does on Kiln

AI agents call cache_model as a supporting operation in Kiln workflows.

WHY IT NEEDS A POLICY

Why cache_model needs a policy

With no description available, the tool's behavior can only be guessed from its name. 'cache_model' likely stores a 3D model in a local cache (a Write-like operation), but it could also involve reading or other side effects. Given the ambiguity, confidence is low. Severity is medium because misuse in a 3D printing context could affect print jobs or stored models, but without description, certainty is low.

From the tool's definition Tool name is 'cache_model' but description is empty and uninformative.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

cache_model Rate-limited

cache_model gets a rate cap, and everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "cache_model": {
      "limits": [
        {
          "counter": "cache_model_rate",
          "window": "minute",
          "max": 60,
          "scope": "grant"
        }
      ]
    }
  }
}

SET A RULE FOR THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Kiln, so you can run agents against it safely.

FAQ

Questions about cache_model

What does the cache_model tool do? +

cache_model. It is categorised as a Other tool in the Kiln MCP Server, which means it performs auxiliary operations.

How do I enforce a policy on cache_model? +

Register the Kiln MCP server in PolicyLayer and add a rule for cache_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.

What risk level is cache_model? +

cache_model is a Other tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit cache_model? +

Yes. Add a rate_limit block to the cache_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.

How do I block cache_model completely? +

Set action: deny in the PolicyLayer policy for cache_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.

What MCP server provides cache_model? +

cache_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.