Controls Headless vs GUI state of a VM.
AI agents invoke set_display_mode to trigger actions in Virtualbox MCP Server. 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 changes the operational display mode of a running VM (headless vs GUI), which triggers an external operation affecting the VM's runtime state. It's not purely a data write nor destructive, but it executes a state change on a live virtual machine, making Execute the most appropriate category. Misuse could disrupt running workloads or expose VM interfaces unexpectedly.
From the tool's definition Controls Headless vs GUI state of a VM
Attacks that exploit this kind of access
Controls Headless vs GUI state of a VM. It is categorised as a Execute tool in the Virtualbox MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Virtualbox MCP Server MCP server in PolicyLayer and add a rule for set_display_mode: 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 Virtualbox MCP Server. Nothing to install.
set_display_mode 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 set_display_mode 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 set_display_mode. 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.
set_display_mode is provided by the Virtualbox MCP Server MCP server (usemanusai/virtualbox-mcp-server). 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 →