publish_model · Kiln MCP: Risk & Policy

WHAT IT DOES

What publish_model does on Kiln

AI agents use publish_model to create or update resources in Kiln — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Kiln environment.

WHY IT NEEDS A POLICY

Why publish_model needs a policy

The name 'publish_model' indicates creation or modification of data in an external system (likely a model repository, marketplace, or cloud service). This is a Write operation—reversible and non-destructive—rather than Read (no retrieval of existing data), Execute (no arbitrary code execution), or Destructive (no deletion).

From the tool's definition Tool name 'publish_model' suggests sharing or uploading a 3D model to an external platform or repository. No description provided, limiting precision.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

publish_model Rate-limited

publish_model stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "publish_model": {
      "limits": [
        {
          "counter": "publish_model_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT 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 publish_model

What does the publish_model tool do? +

publish_model. It is categorised as a Write tool in the Kiln MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on publish_model? +

Register the Kiln MCP server in PolicyLayer and add a rule for publish_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 publish_model? +

publish_model is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit publish_model? +

Yes. Add a rate_limit block to the publish_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 publish_model completely? +

Set action: deny in the PolicyLayer policy for publish_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 publish_model? +

publish_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.