datasets_list
AI agents call datasets_list to retrieve information from Kaggle-MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries a list of datasets from Kaggle, producing no side effects. It follows the naming convention of other read-only enumeration tools on the server. Even without an explicit description, the semantic meaning of 'list' combined with the context of a data browsing/analysis platform indicates a read-only query operation with low risk if misused by an AI agent.
From the tool's definition Tool name 'datasets_list' indicates listing/retrieval of datasets. No description provided, but consistent with sibling tools like 'competitions_list', 'competition_list_files', and 'competition_leaderboard' which are all read operations that query and return…
Attacks that exploit this kind of access
datasets_list. 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 datasets_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.
datasets_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 datasets_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 datasets_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.
datasets_list 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.
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 →