Preview samples from a dataset
AI agents call dataset_preview to retrieve information from ML Lab MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only retrieves and displays sample data from datasets. It has no side effects, does not execute code, does not modify data, and does not delete anything. It is a straightforward read operation with minimal blast radius if misused by an AI agent, as the worst outcome would be accessing potentially sensitive dataset contents already within the ML Lab environment.
From the tool's definition Tool name is 'dataset_preview' and description states it 'Preview samples from a dataset' — this is a read-only retrieval operation that queries data without modifying or executing anything.
Attacks that exploit this kind of access
Preview samples from a dataset. It is categorised as a Read tool in the ML Lab MCP MCP Server, which means it retrieves data without modifying state.
Register the ML Lab MCP server in PolicyLayer and add a rule for dataset_preview: 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 ML Lab MCP. Nothing to install.
dataset_preview 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_preview 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_preview. 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_preview is provided by the ML Lab MCP server (pushpullcommitpush/ml-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 →