Return descriptive statistics for a loaded dataset.
AI agents call dataset_summary to retrieve information from Feature Evaluation MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and calculates summary statistics (descriptive metrics) from an already-loaded dataset. It has no side effects, does not modify data, does not execute user-supplied code, and does not delete or move data. It is a pure read operation, making it the lowest risk category.
From the tool's definition Tool name 'dataset_summary' and description 'Return descriptive statistics for a loaded dataset' indicates a retrieval operation that computes and returns statistics without modifying, deleting, or executing arbitrary code on the dataset.
Attacks that exploit this kind of access
Return descriptive statistics for a loaded dataset. It is categorised as a Read tool in the Feature Evaluation MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Feature Evaluation MCP Server MCP server in PolicyLayer and add a rule for dataset_summary: 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 Feature Evaluation MCP Server. Nothing to install.
dataset_summary 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_summary 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_summary. 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_summary is provided by the Feature Evaluation MCP Server MCP server (jaivardhan1209/featureengineering). 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 →