AI agents invoke start_movie_rec 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 triggers a camera to start recording video—an external operation with side effects that cannot be trivially reversed (requires stopping the recording separately). It is Execute rather than Write because it activates a physical device, not just data modification. It is not Destructive because recording can be stopped and footage preserved or deleted by user choice afterward.
From the tool's definition Tool name 'start_movie_rec' indicates initiation of movie recording on a remote Sony DSC camera. Server description confirms the tool controls a physical camera device via Camera Remote API, supporting 'shooting' operations.
Attacks that exploit this kind of access
start_movie_rec. 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_movie_rec: 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_movie_rec 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_movie_rec 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_movie_rec. 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_movie_rec 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 →