Select top-K features using a univariate scoring function.
AI agents call select_k_best 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.
The tool performs a read-only statistical evaluation, scoring and ranking features from an existing dataset. It does not write, execute code, delete data, or involve financial transactions. Misuse potential is minimal as it only returns feature rankings.
From the tool's definition 'Select top-K features using a univariate scoring function' — this is a statistical analysis/query operation that retrieves ranked features without modifying any data.
Attacks that exploit this kind of access
Select top-K features using a univariate scoring function. 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 select_k_best: 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.
select_k_best 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 select_k_best 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 select_k_best. 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.
select_k_best 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 →