Send an arbitrary SCPI query to the oscilloscope and return the response. Use this as an escape hatch for commands not covered by other tools. Note: CHDR is set to OFF, so responses contain only values (no headers).
AI agents invoke scpi_query to trigger actions in Siglent Sds. 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 SCPI commands to a physical oscilloscope. While framed as a 'query', arbitrary SCPI access can reconfigure, reset, or otherwise affect the instrument in ways beyond simple reads. The 'escape hatch for commands not covered by other tools' phrasing confirms it can execute any SCPI command, including those that modify device state.
From the tool's definition 'Send an arbitrary SCPI query to the oscilloscope' and 'Use this as an escape hatch for commands not covered by other tools'
Attacks that exploit this kind of access
Send an arbitrary SCPI query to the oscilloscope and return the response. Use this as an escape hatch for commands not covered by other tools. Note: CHDR is set to OFF, so responses contain only values (no headers). It is categorised as a Execute tool in the Siglent Sds MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Siglent Sds MCP server in PolicyLayer and add a rule for scpi_query: 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 Siglent Sds. Nothing to install.
scpi_query 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 scpi_query 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 scpi_query. 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.
scpi_query is provided by the Siglent Sds MCP server (magnusjohansson/siglent-sds-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 →