Switch focus to a window with the specified title.
AI agents invoke switch_to_window to trigger actions in Simple 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 performs a system-level UI action by switching focus between windows, which is an external operation that affects the running environment. It triggers an OS-level action (window focus change) rather than simply reading data or writing a file. Misuse could allow an AI agent to hijack focus from security-sensitive windows or interfere with user activity.
From the tool's definition Switch focus to a window with the specified title
Attacks that exploit this kind of access
Switch focus to a window with the specified title. It is categorised as a Execute tool in the Simple MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Simple MCP server in PolicyLayer and add a rule for switch_to_window: 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 Simple MCP. Nothing to install.
switch_to_window 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 switch_to_window 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 switch_to_window. 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.
switch_to_window is provided by the Simple MCP server (karar-hayder/simple-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 →