AI agents invoke open_camera_preview_tool to trigger actions in xigua-MCP. 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 activates the system camera and starts a background preview process. It is an external operation with real-world side effects (camera activation, potential privacy implications), placing it in the Execute category. It does not delete data or move money, but misuse could violate privacy by silently activating the camera.
From the tool's definition 打开摄像头实时预览窗口 (Opens a camera live preview window) — triggers an external operation (activating the camera hardware and launching a preview process) that runs in the background
Attacks that exploit this kind of access
打开摄像头实时预览窗口。此工具会立即返回成功,预览在后台运行。. It is categorised as a Execute tool in the xigua-MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the xigua- MCP server in PolicyLayer and add a rule for open_camera_preview_tool: 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 xigua-MCP. Nothing to install.
open_camera_preview_tool 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 open_camera_preview_tool 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 open_camera_preview_tool. 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.
open_camera_preview_tool is provided by the xigua- MCP server (xiguaxiaome/xigua-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 →