Switch to a specific application window (e.g.,
AI agents invoke Switch-Tool to trigger actions in Windows-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 triggers an OS-level action that changes the focused application window, which is an external operation affecting the desktop environment. It's not a read (no data retrieval), not destructive, but it does execute a UI automation action that changes system state. Misuse could allow an agent to switch context to sensitive applications like banking or password managers, enabling further exploitation.
From the tool's definition Switch to a specific application window
Attacks that exploit this kind of access
Switch to a specific application window (e.g.,. It is categorised as a Execute tool in the Windows-MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Windows- MCP server in PolicyLayer and add a rule for Switch-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 Windows-MCP. Nothing to install.
Switch-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 Switch-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 Switch-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.
Switch-Tool is provided by the Windows- MCP server (stepbystep-1/winows-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 →