AI agents invoke stop_bulb 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 executes a command to a remote camera device that produces a physical side effect (shutter closure). While not destructive to data and not financial, it is an Execute-class action because it triggers external operations on hardware. The severity is medium: misuse could waste photos or interrupt legitimate shooting, but cannot corrupt data or cause financial loss.
From the tool's definition 'Close the bulb shutter' — directly controls camera hardware (shutter mechanism), triggering an external physical operation whose effects depend on the camera state and timing arguments.
Attacks that exploit this kind of access
Close the bulb shutter. 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 stop_bulb: 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.
stop_bulb 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 stop_bulb 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 stop_bulb. 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.
stop_bulb 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 →