model_create_new · Kaggle- MCP: Risk & Policy

WHAT IT DOES

What model_create_new does on Kaggle-MCP

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

WHY IT NEEDS A POLICY

Why model_create_new needs a policy

This tool creates a new model resource on Kaggle, which is a reversible Write operation. It modifies the user's Kaggle account state by adding a new model artifact, but the action can be undone by deletion. Severity is medium because unauthorized model creation could consume account resources, clutter the user's model registry, or be used for spam/abuse, but it does not delete data or commit financial obligations.

From the tool's definition Tool name 'model_create_new' and description 'Create a new model' indicate creation of a new resource on the Kaggle platform.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

model_create_new Rate-limited

model_create_new 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": {
    "model_create_new": {
      "limits": [
        {
          "counter": "model_create_new_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 Kaggle-MCP, so you can run agents against it safely.

FAQ

Questions about model_create_new

What does the model_create_new tool do? +

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

How do I enforce a policy on model_create_new? +

Register the Kaggle- MCP server in PolicyLayer and add a rule for model_create_new: 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 Kaggle-MCP. Nothing to install.

What risk level is model_create_new? +

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

Can I rate-limit model_create_new? +

Yes. Add a rate_limit block to the model_create_new 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 model_create_new completely? +

Set action: deny in the PolicyLayer policy for model_create_new. 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 model_create_new? +

model_create_new is provided by the Kaggle- MCP server (realbytecode/kaggle-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.