camera_control
AI agents invoke camera_control to trigger actions in Homeassistant. 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.
Based on the name and server context, this tool likely controls camera devices (e.g., enable/disable recording, pan/tilt, snapshots). 'Control' implies triggering external operations on physical devices. This is most consistent with Execute. However, the empty description significantly lowers confidence. Severity is medium given potential privacy implications of camera manipulation.
From the tool's definition Tool name 'camera_control' on a Home Assistant MCP server that 'controls devices and services'; description is empty and uninformative.
Attacks that exploit this kind of access
camera_control. It is categorised as a Execute tool in the Homeassistant MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Homeassistant MCP server in PolicyLayer and add a rule for camera_control: 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 Homeassistant. Nothing to install.
camera_control 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 camera_control 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 camera_control. 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.
camera_control is provided by the Homeassistant MCP server (robbrad/homeassistant-mcp). 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 →