list_windows
Lists on-screen windows of any app with window_id, owning app bundle id + name, title, bounds (global space, top-left, points), display_id, and is_focused. Window TITLES require Screen Recording permission — without it this returns an explicit permission_required error rather than a title-less re...
This record as markdown: /tools/com-local-mcp-local-mcp/list-windows.md
What list_windows does on Local
AI agents call list_windows to retrieve information from Local without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
app_bundle_id | string | — | Only return windows owned by this app bundle id. |
on_screen_only | boolean | — | Only on-screen windows (default true). |
Parameters from the server's own tool schema.
Why list_windows is rated Low
This tool retrieves and queries window state information from the operating system. It performs no data modification, deletion, code execution, or financial operations. The permission requirement for Screen Recording is a security gate, not a category change. The stable window_id for 'later targeting' suggests it may facilitate other tool operations, but the tool itself is purely informational.
From the tool's definition Tool description states it 'Lists on-screen windows' and 'returns' window metadata (window_id, app bundle id, name, title, bounds, display_id, is_focused). The verb 'lists' and 'returns' indicate read-only data retrieval with no modification or side effects.
Attacks that exploit this kind of access
The rule that runs list_windows 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 list_windows, this is the rule to start with:
list_windows is read-only, so it stays allowed. 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 list_windows call is checked against it from then on.
Questions about list_windows
Lists on-screen windows of any app with window_id, owning app bundle id + name, title, bounds (global space, top-left, points), display_id, and is_focused. Window TITLES require Screen Recording permission — without it this returns an explicit permission_required error rather than a title-less result. Optional app_bundle_id filter. window_id is stable within the session for later targeting. It is categorised as a Read tool in the Local MCP Server, which means it retrieves data without modifying state.
list_windows accepts 2 parameters: app_bundle_id, on_screen_only. 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 list_windows: 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.
list_windows is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the list_windows 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 list_windows. 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.
list_windows 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.
This server
Across the catalogue