scope_stop · LeCroy Oscilloscope MCP: Risk & Policy

WHAT IT DOES

What scope_stop does on LeCroy Oscilloscope MCP

AI agents invoke scope_stop to trigger actions in LeCroy Oscilloscope 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 scope_stop needs a policy

This tool executes a command that changes the operational state of hardware equipment. While not destructive (data is retained and acquisition can be restarted), it actively triggers an external operation whose effects depend on timing and context. It fits Execute rather than Read (not passive query) or Write (not creating/modifying data reversibly—stopping acquisition is a state change operation).

From the tool's definition Tool performs immediate action 'Stop acquisition' on oscilloscope hardware via SCPI command (STOP). This triggers external operation with effects that persist until reversed by separate command (e.g., scope_arm to restart).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

scope_stop Rate-limited

scope_stop 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": {
    "scope_stop": {
      "limits": [
        {
          "counter": "scope_stop_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 LeCroy Oscilloscope MCP, so you can run agents against it safely.

FAQ

Questions about scope_stop

What does the scope_stop tool do? +

Stop acquisition immediately (STOP). It is categorised as a Execute tool in the LeCroy Oscilloscope 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 scope_stop? +

Register the LeCroy Oscilloscope MCP server in PolicyLayer and add a rule for scope_stop: 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 LeCroy Oscilloscope MCP. Nothing to install.

What risk level is scope_stop? +

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

Can I rate-limit scope_stop? +

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

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

scope_stop is provided by the LeCroy Oscilloscope MCP server (lucasgerads/lecroy-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.