kernel_pull

What kernel_pull does on Kaggle-MCP

AI agents call kernel_pull to retrieve information from Kaggle-MCP without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Why kernel_pull is rated Low

Without an explicit description, classification relies on naming convention and context. 'Pull' typically indicates retrieval rather than modification or execution. The Kaggle kernel context suggests downloading or fetching notebook/script content, which is a read operation. Confidence is moderate (0.7) due to empty description; if 'kernel_pull' actually executes kernels, it would be Execute instead.

From the tool's definition Tool name 'kernel_pull' suggests retrieving or downloading kernel code/data from Kaggle. The method naming pattern 'pull' is consistent with fetching operations.

The rule that runs kernel_pull safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Kaggle-MCP, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For kernel_pull, this is the rule to start with:

{
  "version": "1",
  "default": "deny",
  "tools": {
    "kernel_pull": {}
  }
}

Questions about kernel_pull