This record as markdown: /tools/alexgladkov-claude-in-mobile/desktop-windows.md
What desktop_windows does on Claude Mobile
AI agents call desktop_windows to retrieve information from Claude Mobile without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why desktop_windows is rated Low
This tool performs information retrieval ('Get...info') about desktop windows, which is consistent with the Read category. It has no side effects, does not execute commands, and does not modify or delete data. The low severity reflects the minimal security risk of querying window metadata.
From the tool's definition Tool name 'desktop_windows' and description 'Get desktop window info' indicate a read-only operation that retrieves or queries information about desktop windows without modifying, executing, or deleting anything.
Attacks that exploit this kind of access
The rule that runs desktop_windows safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Claude Mobile, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For desktop_windows, this is the rule to start with:
desktop_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 Claude Mobile, apply this rule, and every desktop_windows call is checked against it from then on.
Questions about desktop_windows
Get desktop window info. It is categorised as a Read tool in the Claude Mobile MCP Server, which means it retrieves data without modifying state.
Register the Claude Mobile MCP server in PolicyLayer and add a rule for desktop_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 Claude Mobile. Nothing to install.
desktop_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 desktop_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 desktop_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.
desktop_windows is provided by the Claude Mobile MCP server (alexgladkov/claude-in-mobile). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Claude Mobile, and thousands of servers like it.
This server
Across the catalogue