Open a local OpenCV preview window for up to N seconds (max 120).
AI agents invoke webcam_preview to trigger actions in farshid-mcp-imageProcessing. 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 triggers an external operation — opening a GUI/preview window using OpenCV — which has side effects on the local system (UI rendering, window management, potential camera access). It goes beyond simply reading data and actively executes a real-time display process on the host machine.
From the tool's definition Open a local OpenCV preview window for up to N seconds (max 120)
Attacks that exploit this kind of access
Open a local OpenCV preview window for up to N seconds (max 120). It is categorised as a Execute tool in the farshid-mcp-imageProcessing MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the farshid-mcp-imageProcessing MCP server in PolicyLayer and add a rule for webcam_preview: 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 farshid-mcp-imageProcessing. Nothing to install.
webcam_preview 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 webcam_preview 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 webcam_preview. 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.
webcam_preview is provided by the farshid-mcp-imageProcessing MCP server (pirahansiah/farshid-mcp-imageprocessing). 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 →