This record as markdown: /tools/54yyyu-kaggle-mcp/dataset-metadata.md
What dataset_metadata does on Kaggle-MCP
AI agents call dataset_metadata 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 dataset_metadata is rated Low
This tool retrieves metadata about a dataset, which is a read-only query operation. It does not create, modify, delete, execute code, or commit financial obligations. The minimal severity reflects that metadata retrieval cannot harm data integrity or security unless the metadata itself is highly sensitive, which is unlikely in the Kaggle context where datasets are publicly catalogued.
From the tool's definition Tool name is 'dataset_metadata' and description states 'Get dataset metadata.' The verb 'Get' indicates a read operation with no modification or side effects.
Attacks that exploit this kind of access
The rule that runs dataset_metadata 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 dataset_metadata, this is the rule to start with:
dataset_metadata 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 dataset_metadata call is checked against it from then on.
Questions about dataset_metadata
Get dataset metadata. 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 dataset_metadata: 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.
dataset_metadata 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 dataset_metadata 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 dataset_metadata. 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.
dataset_metadata 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