usbtmc_receive
AI agents call usbtmc_receive to retrieve information from USBTMC MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
USBTMC devices are test instruments that return measurement data and status information. A 'receive' operation fetches data from these instruments without modifying their state or configuration. While controlling test equipment carries some operational risk, receiving data itself is a read-only operation with limited blast radius.
From the tool's definition Tool name 'usbtmc_receive' indicates data retrieval from USB Test and Measurement devices. No description provided, but the name pattern and context with sibling tools like usbtmc_send, usbtmc_query, and screenshot tools suggest this receives responses or…
Attacks that exploit this kind of access
usbtmc_receive. It is categorised as a Read tool in the USBTMC MCP Server MCP Server, which means it retrieves data without modifying state.
Register the USBTMC MCP Server MCP server in PolicyLayer and add a rule for usbtmc_receive: 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_receive is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the usbtmc_receive 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_receive. 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_receive 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 →