recursive_feature_elimination

WHAT IT DOES

What recursive_feature_elimination does on Feature Evaluation MCP Server

AI agents invoke recursive_feature_elimination 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.

WHY IT NEEDS A POLICY

Why recursive_feature_elimination needs a policy

RFE is a computational process that iteratively trains models and eliminates features, executing algorithmic operations on data. It runs a model-fitting procedure repeatedly, making it Execute rather than Read (it performs computation with side effects like model training), though it doesn't modify stored data destructively or involve financial operations.

From the tool's definition Perform Recursive Feature Elimination (RFE)

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

recursive_feature_elimination Rate-limited

recursive_feature_elimination stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "recursive_feature_elimination": {
      "limits": [
        {
          "counter": "recursive_feature_elimination_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Feature Evaluation MCP Server, so you can run agents against it safely.

FAQ

Questions about recursive_feature_elimination

What does the recursive_feature_elimination tool do? +

Perform Recursive Feature Elimination (RFE). 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.

How do I enforce a policy on recursive_feature_elimination? +

Register the Feature Evaluation MCP Server MCP server in PolicyLayer and add a rule for recursive_feature_elimination: 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.

What risk level is recursive_feature_elimination? +

recursive_feature_elimination is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit recursive_feature_elimination? +

Yes. Add a rate_limit block to the recursive_feature_elimination 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.

How do I block recursive_feature_elimination completely? +

Set action: deny in the PolicyLayer policy for recursive_feature_elimination. 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.

What MCP server provides recursive_feature_elimination? +

recursive_feature_elimination 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.