AI agents call list_windows to retrieve information from MacWright without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information about open windows and running applications—their names, titles, and screen positions. It has no side effects, does not modify any state, and does not trigger actions. While the information exposed could be used for reconnaissance (e.g., determining what an end-user is viewing), the tool itself is purely informational.
From the tool's definition Tool name 'list_windows' and description state it 'List[s] all visible applications with window titles and bounds' and 'Returns JSON array'. The verb 'list' and the output-only nature (returns data without modification) are characteristic of read operations.
Attacks that exploit this kind of access
List all visible applications with window titles and bounds where available. Returns JSON array of {app, title?, bounds?}. Titles show current document, URL, etc. It is categorised as a Read tool in the MacWright MCP Server, which means it retrieves data without modifying state.
Register the MacWright 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 MacWright. 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 MacWright MCP server (ruchit-p/macwright). 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 →