Search for Kaggle datasets
AI agents call kaggle_search_datasets to retrieve information from Mcp Kaggle Tool without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or lists publicly available dataset metadata from Kaggle without executing code, modifying data, or causing side effects. It is a standard read operation that returns search results. The low severity reflects minimal blast radius—an AI agent misusing this tool would only retrieve unintended dataset information, with no ability to modify, delete, or execute anything.
From the tool's definition Tool name 'kaggle_search_datasets' and description 'Search for Kaggle datasets' indicate a query/retrieval operation with no modification or execution of code.
Attacks that exploit this kind of access
Search for Kaggle datasets. It is categorised as a Read tool in the Mcp Kaggle Tool MCP Server, which means it retrieves data without modifying state.
Register the Mcp Kaggle Tool MCP server in PolicyLayer and add a rule for kaggle_search_datasets: 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 Mcp Kaggle Tool. Nothing to install.
kaggle_search_datasets 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 kaggle_search_datasets 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 kaggle_search_datasets. 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.
kaggle_search_datasets is provided by the Mcp Kaggle Tool MCP server (mikeybeez/mcp-kaggle-tool). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →