This record as markdown: /tools/54yyyu-kaggle-mcp/kernels-list.md
What kernels_list does on Kaggle-MCP
AI agents call kernels_list 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 kernels_list is rated Low
The tool appears to list or retrieve kernel information from Kaggle. As a 'list' operation with no indication of side effects, destructive capability, or external command execution, this is a Read operation. Severity is low because listing public or user-accessible kernels poses minimal risk even if misused by an AI agent.
From the tool's definition Tool name 'kernels_list' indicates a list/query operation. No description provided, but naming convention and context among sibling tools (competition_list_files, competitions_list) suggest data retrieval without modification.
Attacks that exploit this kind of access
The rule that runs kernels_list 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 kernels_list, this is the rule to start with:
kernels_list is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Kaggle-MCP, apply this rule, and every kernels_list call is checked against it from then on.
Questions about kernels_list
kernels_list is a read tool on the Kaggle MCP server. It is categorised as a Read tool in the Kaggle-MCP MCP Server, which means it retrieves data without modifying state.
Register the Kaggle MCP server in PolicyLayer and add a rule for kernels_list: 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.
kernels_list is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the kernels_list 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.
Set action: deny in the PolicyLayer policy for kernels_list. 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.
kernels_list is provided by the Kaggle MCP server (54yyyu/kaggle-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Kaggle, and thousands of servers like it.
This server
Across the catalogue