stop_training_tool · Qiskit Gym MCP Server MCP

WHAT IT DOES

What stop_training_tool does on Qiskit Gym MCP Server

AI agents invoke stop_training_tool to trigger actions in Qiskit Gym 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_tool needs a policy

This tool triggers an external operation (halting a quantum circuit synthesis training session) whose effects depend on which training session is targeted. While not destructive (training data/results are not deleted), it executes a state-changing command on a running process. The medium severity reflects that stopping a training session is disruptive but recoverable—training can be restarted.

From the tool's definition Tool name 'stop_training_tool' with description 'Stop a training session' indicates execution of a control action that terminates an active process.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

stop_training_tool Rate-limited

stop_training_tool 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_tool": {
      "limits": [
        {
          "counter": "stop_training_tool_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 Qiskit Gym MCP Server, so you can run agents against it safely.

FAQ

Questions about stop_training_tool

What does the stop_training_tool tool do? +

Stop a training session. It is categorised as a Execute tool in the Qiskit Gym 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_tool? +

Register the Qiskit Gym MCP Server MCP server in PolicyLayer and add a rule for stop_training_tool: 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 Qiskit Gym MCP Server. Nothing to install.

What risk level is stop_training_tool? +

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

Can I rate-limit stop_training_tool? +

Yes. Add a rate_limit block to the stop_training_tool 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_tool completely? +

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

stop_training_tool is provided by the Qiskit Gym MCP Server MCP server (qiskit-gym-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.