usbtmc_send
AI agents invoke usbtmc_send to trigger actions in USBTMC MCP Server. 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 name 'usbtmc_send' on a USBTMC/SCPI instrument control server almost certainly sends SCPI commands to test and measurement hardware. Sending arbitrary SCPI commands to lab instruments can trigger physical operations (e.g., high-voltage outputs, relay switching, waveform generation), making this an Execute-level action.
From the tool's definition Tool name 'usbtmc_send' on a server that 'Enables controlling multiple USBTMC devices simultaneously using SCPI commands'. Sibling tool 'usbtmc_query' suggests send is the write/command counterpart.
Attacks that exploit this kind of access
usbtmc_send. It is categorised as a Execute tool in the USBTMC MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the USBTMC MCP Server MCP server in PolicyLayer and add a rule for usbtmc_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 USBTMC MCP Server. Nothing to install.
usbtmc_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 usbtmc_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 usbtmc_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.
usbtmc_send is provided by the USBTMC MCP Server MCP server (naonaome/usbtmc-lite-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 →