Arm the trigger (ARM). Start waiting for a trigger event.
AI agents invoke scope_arm 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.
The tool directly commands a physical instrument (LeCroy oscilloscope) to arm and begin active measurement operations. While not destructive or financial, arming a trigger initiates hardware-level state changes and measurement acquisition whose outcome depends on external conditions (input signals, trigger settings).
From the tool's definition Tool description states 'Arm the trigger (ARM). Start waiting for a trigger event.' - this triggers external hardware operations on a physical oscilloscope whose effects depend on the instrument state and signal conditions.
Attacks that exploit this kind of access
Arm the trigger (ARM). Start waiting for a trigger event. 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.
Register the LeCroy Oscilloscope MCP server in PolicyLayer and add a rule for scope_arm: 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.
scope_arm is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the scope_arm 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.
Set action: deny in the PolicyLayer policy for scope_arm. 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.
scope_arm 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.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →