Compute permutation importance on a held-out test set.
AI agents invoke permutation_importance_analysis to trigger actions in Feature Evaluation MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool runs a computational analysis (permutation importance) by executing model evaluations on a dataset. It involves running a model multiple times with permuted features to measure importance — an active computation/execution process. It does not merely read stored data but triggers model execution. No data is permanently modified or deleted, so it does not qualify as Destructive or Write.
From the tool's definition Compute permutation importance on a held-out test set
Attacks that exploit this kind of access
Compute permutation importance on a held-out test set. It is categorised as a Execute tool in the Feature Evaluation MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Feature Evaluation MCP Server MCP server in PolicyLayer and add a rule for permutation_importance_analysis: 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.
permutation_importance_analysis is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the permutation_importance_analysis 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 permutation_importance_analysis. 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.
permutation_importance_analysis 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.
permutation_importance_analysis is one line of Feature Evaluation MCP Server's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →