kernel_output

What kernel_output does on Kaggle-MCP

AI agents call kernel_output 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_output is rated Low

The tool appears designed to fetch or retrieve output results from previously executed kernels. This is a read-only operation with no side effects—it queries existing data. The low confidence reflects the empty description; if the tool actually executes kernels (rather than just retrieving their output), it would be Execute instead.

From the tool's definition Tool name 'kernel_output' suggests retrieving output from a Kaggle kernel/notebook execution. No description provided, but naming convention and context within a Kaggle API connector imply data retrieval rather than modification or execution.

The rule that runs kernel_output 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_output, this is the rule to start with:

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

Questions about kernel_output