trainClassifier · Infer MCP Server MCP: Risk & Policy

WHAT IT DOES

What trainClassifier does on Infer MCP Server

AI agents invoke trainClassifier to trigger actions in Infer 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 trainClassifier needs a policy

This tool executes code/commands on remote systems via SSH, which is characteristic of the Execute category. The blast radius is high because SSH command execution can have significant side effects depending on what commands are run—training could consume resources, modify system state, or trigger unintended operations.

From the tool's definition Tool description states 'Run classifier training commands on a remote host via SSH'. The name 'trainClassifier' combined with 'remote host via SSH' indicates execution of arbitrary commands on external systems.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

trainClassifier Rate-limited

trainClassifier 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": {
    "trainClassifier": {
      "limits": [
        {
          "counter": "trainclassifier_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 Infer MCP Server, so you can run agents against it safely.

FAQ

Questions about trainClassifier

What does the trainClassifier tool do? +

Run classifier training commands on a remote host via SSH. It is categorised as a Execute tool in the Infer 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 trainClassifier? +

Register the Infer MCP Server MCP server in PolicyLayer and add a rule for trainClassifier: 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 Infer MCP Server. Nothing to install.

What risk level is trainClassifier? +

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

Can I rate-limit trainClassifier? +

Yes. Add a rate_limit block to the trainClassifier 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 trainClassifier completely? +

Set action: deny in the PolicyLayer policy for trainClassifier. 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 trainClassifier? +

trainClassifier is provided by the Infer MCP Server MCP server (jackyxhb/infermcpserver). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.