create_training_job · NeuronSearchLab MCP: Risk & Policy

WHAT IT DOES

What create_training_job does on NeuronSearchLab

AI agents invoke create_training_job to trigger actions in NeuronSearchLab. 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 create_training_job needs a policy

This tool initiates an external computation process (model training) and upon completion overwrites the currently deployed model. It is Execute because it triggers an external operation with significant side effects; the model replacement is impactful (high severity) since it changes the live recommendation engine for all users, but the previous model is not explicitly destroyed/purged in an irreversible way —…

From the tool's definition 'Trigger a new model training job' and 'replaces the current model when complete'

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

create_training_job Rate-limited

create_training_job 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": {
    "create_training_job": {
      "limits": [
        {
          "counter": "create_training_job_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 NeuronSearchLab, so you can run agents against it safely.

FAQ

Questions about create_training_job

What does the create_training_job tool do? +

Trigger a new model training job. The job trains on all available interaction data and replaces the current model when complete. It is categorised as a Execute tool in the NeuronSearchLab MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on create_training_job? +

Register the NeuronSearchLab MCP server in PolicyLayer and add a rule for create_training_job: 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 NeuronSearchLab. Nothing to install.

What risk level is create_training_job? +

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

Can I rate-limit create_training_job? +

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

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

create_training_job is provided by the NeuronSearchLab MCP server (neuronsearchlab/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.