Send raw SCPI command (no response)
AI agents invoke vna_scpi_send to trigger actions in Copper Mountain Vna. 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.
This tool sends arbitrary raw SCPI commands to physical lab hardware (a VNA). Since it accepts any SCPI command, it can trigger any operation the instrument supports — including reconfiguring sweeps, overwriting calibrations, changing hardware settings, or issuing destructive commands. The 'no response' note means it fires-and-forgets with no safety feedback.
From the tool's definition "Send raw SCPI command (no response)" — executes arbitrary raw SCPI commands on a Vector Network Analyzer over TCP/IP
Attacks that exploit this kind of access
Send raw SCPI command (no response). It is categorised as a Execute tool in the Copper Mountain Vna MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Copper Mountain Vna MCP server in PolicyLayer and add a rule for vna_scpi_send: 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 Copper Mountain Vna. Nothing to install.
vna_scpi_send 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 vna_scpi_send 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 vna_scpi_send. 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.
vna_scpi_send is provided by the Copper Mountain Vna MCP server (rfingadam/copper-mountain-vna-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 →