experiment_create · ML Lab MCP: Risk & Policy

WHAT IT DOES

What experiment_create does on ML Lab MCP

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

WHY IT NEEDS A POLICY

Why experiment_create needs a policy

The tool creates (writes) a new experiment entry, which is a reversible operation. It does not execute arbitrary code, delete data, or move money. However, severity is elevated to medium because experiments in an ML engineering context may trigger resource allocation, cost accumulation, or GPU reservations depending on implementation.

From the tool's definition Tool name 'experiment_create' and description 'Create a new experiment' indicate data creation. This is a reversible write operation that adds a new experiment record to the ML Lab environment.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

experiment_create Rate-limited

experiment_create 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": {
    "experiment_create": {
      "limits": [
        {
          "counter": "experiment_create_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 ML Lab MCP, so you can run agents against it safely.

FAQ

Questions about experiment_create

What does the experiment_create tool do? +

Create a new experiment. It is categorised as a Write tool in the ML Lab MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on experiment_create? +

Register the ML Lab MCP server in PolicyLayer and add a rule for experiment_create: 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 ML Lab MCP. Nothing to install.

What risk level is experiment_create? +

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

Can I rate-limit experiment_create? +

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

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

experiment_create is provided by the ML Lab MCP server (pushpullcommitpush/ml-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.