stop_training · Ultralytics MCP Server MCP: Risk & Policy

WHAT IT DOES

What stop_training does on Ultralytics MCP Server

AI agents invoke stop_training to trigger actions in Ultralytics MCP Server. 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 stop_training needs a policy

Stopping a training job is an executable action that triggers a state change in an external system (the YOLO training process). While not destructive (training can resume) or financial, it is an active operation that interrupts workflows and could have unintended consequences if triggered inappropriately.

From the tool's definition Tool name 'stop_training' and description 'Stop currently running training job' indicate an external operation that interrupts an active process.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

stop_training Rate-limited

stop_training 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": {
    "stop_training": {
      "limits": [
        {
          "counter": "stop_training_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 Ultralytics MCP Server, so you can run agents against it safely.

FAQ

Questions about stop_training

What does the stop_training tool do? +

Stop currently running training job. It is categorised as a Execute tool in the Ultralytics MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on stop_training? +

Register the Ultralytics MCP Server MCP server in PolicyLayer and add a rule for stop_training: 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 Ultralytics MCP Server. Nothing to install.

What risk level is stop_training? +

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

Can I rate-limit stop_training? +

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

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

stop_training is provided by the Ultralytics MCP Server MCP server (metehanyasar11/ultralytics_mcp_server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.