Inspect a dataset
AI agents call dataset_inspect 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.
The tool retrieves or queries dataset information for inspection purposes. The verb 'inspect' denotes viewing/examining without side effects. No data is modified, executed, or deleted. This is a straightforward Read operation with minimal risk—an AI agent could only extract information about datasets, not alter them or trigger computational operations.
From the tool's definition Tool name 'dataset_inspect' and description 'Inspect a dataset' indicate read-only querying of dataset contents with no modification, deletion, or execution capabilities.
Attacks that exploit this kind of access
Inspect 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_inspect: 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_inspect 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_inspect 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_inspect. 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_inspect 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 →