AI agents invoke start_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.
The tool executes a real-world physical action (opening the camera shutter) that affects the external environment. This is an Execute category tool because it triggers an external operation that cannot be easily reversed and whose outcome depends on context (lighting, subject, duration). While not strictly irreversible (the shutter can be closed via 'stop_bulb'), it commits the camera to a specific physical action.
From the tool's definition Tool is called 'start_bulb' and described as 'Open the shutter for bulb exposure.' This directly triggers a camera action—opening the shutter—which is an external operation whose effects depend on camera state and context.
Attacks that exploit this kind of access
Open the shutter for bulb exposure. Camera must be in Manual. 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_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.
start_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 start_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 start_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.
start_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 →