AI agents invoke start_burst to trigger actions in So Dsc. 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 remotely executes a camera action that produces observable external effects (photos capture). While not destructive or financial, it is an Execute-category tool because it triggers an external operation via the Camera Remote API. Severity is high because an AI agent could rapidly exhaust camera battery, fill storage, or take unwanted photos if the burst parameters are not carefully controlled.
From the tool's definition 'Start continuous (burst) shooting' — triggers physical camera hardware operation whose effects (photos taken, storage consumed, battery drained) depend on camera state and timing arguments.
Attacks that exploit this kind of access
Start continuous (burst) shooting. Camera must already be in still. It is categorised as a Execute tool in the So Dsc MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the So Dsc MCP server in PolicyLayer and add a rule for start_burst: 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.
start_burst 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 start_burst 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 start_burst. 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.
start_burst 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 →