start_run · MCP DS Toolkit Server MCP: Risk & Policy

WHAT IT DOES

What start_run does on MCP DS Toolkit Server

AI agents use start_run 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 start_run needs a policy

This tool creates a new run record within an experiment, which is a reversible write operation. It generates/initializes data but does not execute code, delete anything, or involve financial transactions. The blast radius is low since starting a run is a routine experiment tracking action.

From the tool's definition Start a new run within an experiment

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

start_run Rate-limited

start_run 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": {
    "start_run": {
      "limits": [
        {
          "counter": "start_run_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 start_run

What does the start_run tool do? +

Start a new run within an experiment. 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 start_run? +

Register the MCP DS Toolkit Server MCP server in PolicyLayer and add a rule for start_run: 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 start_run? +

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

Can I rate-limit start_run? +

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

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

start_run 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.