This record as markdown: /tools/alexgladkov-claude-in-mobile/desktop-resize.md
What desktop_resize does on Claude Mobile
AI agents invoke desktop_resize to trigger actions in Claude Mobile. 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.
Why desktop_resize is rated High
This tool performs an action on a desktop window (resizing it), which is an external operation that modifies the state of the UI environment. It's not a simple read, nor does it create/modify data in a reversible write sense — it manipulates the running system's window manager. It falls under Execute as it triggers an external operation (UI interaction) on the device.
From the tool's definition Resize a desktop window
Attacks that exploit this kind of access
The rule that runs desktop_resize 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_resize, this is the rule to start with:
desktop_resize 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 Claude Mobile, apply this rule, and every desktop_resize call is checked against it from then on.
Questions about desktop_resize
Resize a desktop window. It is categorised as a Execute tool in the Claude Mobile MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Claude Mobile MCP server in PolicyLayer and add a rule for desktop_resize: 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_resize 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 desktop_resize 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_resize. 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_resize 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.
Across the catalogue