Connect to the LeCroy oscilloscope at the given VISA resource address.
AI agents use scope_connect to create or update resources in LeCroy Oscilloscope MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your LeCroy Oscilloscope MCP environment.
While connection establishment itself is not destructive or irreversible, it creates a persistent connection state to remote hardware that enables subsequent control actions. This falls under Write (modifies system state reversibly) rather than Read since it actively changes the connection status.
From the tool's definition Tool establishes a connection to a remote LeCroy oscilloscope device via VISA resource address, modifying the state of the connection/session.
Attacks that exploit this kind of access
Connect to the LeCroy oscilloscope at the given VISA resource address. It is categorised as a Write tool in the LeCroy Oscilloscope MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the LeCroy Oscilloscope MCP server in PolicyLayer and add a rule for scope_connect: 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_connect is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the scope_connect 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_connect. 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_connect 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 →