scope_trigger
AI agents invoke scope_trigger to trigger actions in Oscilloscope. 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.
Triggering an oscilloscope is an Execute action: it commands external hardware to perform an operation (data capture initiation or trigger condition setup) whose effects depend on configuration arguments. While not destructive, not financial, and not a simple read, it actively executes a hardware operation.
From the tool's definition Tool name 'scope_trigger' on an oscilloscope control server with capabilities for 'waveform capture' and 'frequency measurements'.
Attacks that exploit this kind of access
scope_trigger. It is categorised as a Execute tool in the Oscilloscope MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Oscilloscope MCP server in PolicyLayer and add a rule for scope_trigger: 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 Oscilloscope. Nothing to install.
scope_trigger 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_trigger 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_trigger. 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_trigger is provided by the Oscilloscope MCP server (sandraschi/oscilloscope-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 →