create_experiment · NeuronSearchLab MCP: Risk & Policy

WHAT IT DOES

What create_experiment does on NeuronSearchLab

AI agents use create_experiment to create or update resources in NeuronSearchLab — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your NeuronSearchLab environment.

WHY IT NEEDS A POLICY

Why create_experiment needs a policy

This tool creates and persists new experiment data. While creation is reversible (experiments can typically be deleted), the act itself modifies the system state and catalogue. It does not execute arbitrary code or trigger external side effects beyond experiment setup. It is less severe than Destructive (which is irreversible), making it a Write-category tool.

From the tool's definition The tool is named 'create_experiment' and described as 'Create a new A/B experiment comparing pipeline variants.' This performs creation of a new experiment record, which is a write operation that modifies state by adding a new entity to the system.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

create_experiment Rate-limited

create_experiment stays usable, but capped — an agent stuck in a loop can't make hundreds of changes 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_experiment": {
      "limits": [
        {
          "counter": "create_experiment_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

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_experiment

What does the create_experiment tool do? +

Create a new A/B experiment comparing pipeline variants. It is categorised as a Write tool in the NeuronSearchLab MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on create_experiment? +

Register the NeuronSearchLab MCP server in PolicyLayer and add a rule for create_experiment: 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_experiment? +

create_experiment is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit create_experiment? +

Yes. Add a rate_limit block to the create_experiment 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_experiment completely? +

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

create_experiment 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.