AI agents call get_liveview_frame to retrieve information from So Dsc without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries current camera feed data without modifying camera state, settings, or stored content. It is a straightforward read operation analogous to fetching or getting data. The live view stream itself poses minimal risk even if accessed by an AI agent, as it only displays what the camera is currently viewing without triggering any camera actions or affecting the device or stored media.
From the tool's definition Tool returns live preview JPEG data with no parameters for modification or control. Description explicitly states it 'Return[s] the latest live preview JPEG', indicating pure data retrieval with no side effects.
Attacks that exploit this kind of access
Return the latest live preview JPEG (~640x424, ~35KB on RX100M5A). It is categorised as a Read tool in the So Dsc MCP Server, which means it retrieves data without modifying state.
Register the So Dsc MCP server in PolicyLayer and add a rule for get_liveview_frame: 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 So Dsc. Nothing to install.
get_liveview_frame 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 get_liveview_frame 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 get_liveview_frame. 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.
get_liveview_frame is provided by the So Dsc MCP server (nananek/so-dsc). 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 →