dataset_transform · ML Lab MCP: Risk & Policy

WHAT IT DOES

What dataset_transform does on ML Lab MCP

AI agents invoke dataset_transform to trigger actions in ML Lab MCP. 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 dataset_transform needs a policy

While 'transform' could be read as a reversible write operation, in an ML context it typically executes arbitrary transformation logic (templates can include code/expressions) against datasets. The effects are not predictable without seeing the template, and the tool operates in a system designed for executing training scripts and managing ML workflows.

From the tool's definition The tool 'dataset_transform' with description 'Transform a dataset with a template' performs data transformation operations that execute templated logic on datasets.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

dataset_transform Rate-limited

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

FAQ

Questions about dataset_transform

What does the dataset_transform tool do? +

Transform a dataset with a template. It is categorised as a Execute tool in the ML Lab MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on dataset_transform? +

Register the ML Lab MCP server in PolicyLayer and add a rule for dataset_transform: 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 dataset_transform? +

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

Can I rate-limit dataset_transform? +

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

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

dataset_transform 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.