dataset_create_version · Kaggle- MCP: Risk & Policy

WHAT IT DOES

What dataset_create_version does on Kaggle-MCP

AI agents use dataset_create_version 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 dataset_create_version needs a policy

This tool creates a new dataset version, which is a reversible modification operation (Write category). The severity is medium because creating unwanted dataset versions could clutter a user's Kaggle workspace and consume storage, but the action is reversible (versions can be deleted). Confidence is lowered from 0.8 to 0.7 due to the empty description, which limits ability to assess full scope and parameters.

From the tool's definition Tool name is 'dataset_create_version', which indicates creation of a new version of a dataset. The description is empty, providing no further clarification, but the name alone strongly suggests a write operation that creates/modifies versioned data on Kaggle.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

dataset_create_version Rate-limited

dataset_create_version 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": {
    "dataset_create_version": {
      "limits": [
        {
          "counter": "dataset_create_version_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 dataset_create_version

What does the dataset_create_version tool do? +

dataset_create_version. 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 dataset_create_version? +

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

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

Can I rate-limit dataset_create_version? +

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

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

dataset_create_version 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.