split_dataset · MCP DS Toolkit Server MCP: Risk & Policy

WHAT IT DOES

What split_dataset does on MCP DS Toolkit Server

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

WHY IT NEEDS A POLICY

Why split_dataset needs a policy

Splitting a dataset creates new derived datasets (train/validation/test subsets), which is a data creation/modification operation. It does not delete the original data, execute arbitrary code, or involve financial transactions. The blast radius is medium because misuse could corrupt ML experiment data splits, but the operation is reversible.

From the tool's definition Split dataset into train/validation/test sets

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

split_dataset Rate-limited

split_dataset 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": {
    "split_dataset": {
      "limits": [
        {
          "counter": "split_dataset_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 MCP DS Toolkit Server, so you can run agents against it safely.

FAQ

Questions about split_dataset

What does the split_dataset tool do? +

Split dataset into train/validation/test sets. It is categorised as a Write tool in the MCP DS Toolkit Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on split_dataset? +

Register the MCP DS Toolkit Server MCP server in PolicyLayer and add a rule for split_dataset: 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 MCP DS Toolkit Server. Nothing to install.

What risk level is split_dataset? +

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

Can I rate-limit split_dataset? +

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

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

split_dataset is provided by the MCP DS Toolkit Server MCP server (yasserelhaddar/mcp-ds-toolkit-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.