model_instance_version_create · Kaggle- MCP: Risk & Policy

WHAT IT DOES

What model_instance_version_create does on Kaggle-MCP

AI agents use model_instance_version_create 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_instance_version_create needs a policy

The tool name suggests it creates a new version of a model instance on Kaggle, which is a Write operation (creating new data). No description is available to confirm destructive or financial aspects. Severity is medium as misuse could create unwanted model versions or consume storage quota.

From the tool's definition Tool name 'model_instance_version_create' implies creating a new version of a model instance. Description is empty, lowering confidence.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

model_instance_version_create Rate-limited

model_instance_version_create 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_instance_version_create": {
      "limits": [
        {
          "counter": "model_instance_version_create_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_instance_version_create

What does the model_instance_version_create tool do? +

model_instance_version_create. 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_instance_version_create? +

Register the Kaggle- MCP server in PolicyLayer and add a rule for model_instance_version_create: 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_instance_version_create? +

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

Can I rate-limit model_instance_version_create? +

Yes. Add a rate_limit block to the model_instance_version_create 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_instance_version_create completely? +

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

model_instance_version_create 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.