window_focus
Brings a window (by window_id from list_windows) to the front and activates its app. window_not_found if it can't be resolved. Requires Accessibility permission.
This record as markdown: /tools/com-local-mcp-local-mcp/window-focus.md
What window_focus does on Local
AI agents invoke window_focus to trigger actions in Local. 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.
| Parameter | Type | Required | Description |
|---|---|---|---|
window_id | string | Yes |
Parameters from the server's own tool schema.
Why window_focus is rated High
This tool performs a UI/system action by focusing and activating a window, which is an external operation beyond simple data retrieval or modification. It interacts with the OS window manager and requires Accessibility permission. Misuse potential is low as it only changes window focus, not data.
From the tool's definition 'Brings a window to the front and activates its app' — triggers an external UI operation on the system
Attacks that exploit this kind of access
The rule that runs window_focus safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Local, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For window_focus, this is the rule to start with:
window_focus stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Local, apply this rule, and every window_focus call is checked against it from then on.
Questions about window_focus
Brings a window (by window_id from list_windows) to the front and activates its app. window_not_found if it can't be resolved. Requires Accessibility permission. It is categorised as a Execute tool in the Local MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
window_focus accepts 1 parameter: window_id. Required: window_id. The full parameter table on this page comes from the server's own tool schema.
Register the Local MCP server in PolicyLayer and add a rule for window_focus: 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 Local. Nothing to install.
window_focus 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 window_focus 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 window_focus. 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.
window_focus is provided by the Local MCP server (local-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Local, and thousands of servers like it.
Across the catalogue