Capture the oscilloscope screen as a PNG image. Returns a base64-encoded image.
AI agents call screenshot to retrieve information from Siglent Sds without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves visual data from the oscilloscope display without creating, modifying, deleting, or executing any operations on the device. It is purely a data retrieval operation analogous to taking a screenshot, which has no side effects on the oscilloscope's configuration, measurements, or state.
From the tool's definition Tool captures and returns a PNG image of the oscilloscope screen as base64-encoded data. The description explicitly states it returns an image with no modification of oscilloscope state or settings.
Attacks that exploit this kind of access
Capture the oscilloscope screen as a PNG image. Returns a base64-encoded image. It is categorised as a Read tool in the Siglent Sds MCP Server, which means it retrieves data without modifying state.
Register the Siglent Sds MCP server in PolicyLayer and add a rule for screenshot: 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.
screenshot 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 screenshot 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 screenshot. 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.
screenshot 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 →