Get dataset metadata.
AI agents call dataset_metadata 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 metadata about datasets without creating, modifying, deleting, or executing anything. It performs a simple query/fetch operation that returns information only. The blast radius if misused is minimal—an agent could only access or display dataset information it is already authorized to view through the Kaggle API.
From the tool's definition Tool name 'dataset_metadata' and description 'Get dataset metadata' indicate a retrieval operation with no side effects. The verb 'Get' and the context of browsing/querying datasets in the Kaggle API confirm this is a read-only action.
Attacks that exploit this kind of access
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 (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 →