model_update · Kaggle- MCP: Risk & Policy

WHAT IT DOES

What model_update does on Kaggle-MCP

AI agents use model_update 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_update needs a policy

The tool modifies an existing model reversibly—updates can typically be rolled back or replaced with prior versions. This is a Write operation rather than Execute (no arbitrary code is run based on user input) or Destructive (the original model is not permanently deleted).

From the tool's definition Tool name 'model_update' and description 'Update an existing model' indicates modification of existing data (a model artifact) in the Kaggle ecosystem.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

model_update Rate-limited

model_update 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_update": {
      "limits": [
        {
          "counter": "model_update_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_update

What does the model_update tool do? +

Update an existing 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_update? +

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

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

Can I rate-limit model_update? +

Yes. Add a rate_limit block to the model_update 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_update completely? +

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

model_update 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.