desktop_stop

Stop running desktop application

SERVERClaude Mobile SOURCEalexgladkov/claude-in-mobile

High RISK CLASS

Category Execute

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/alexgladkov-claude-in-mobile/desktop-stop.md

WHAT IT DOES

What desktop_stop does on Claude Mobile

AI agents invoke desktop_stop 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.

RISK

Why desktop_stop is rated High

Stopping an application is an Execute-class action because it triggers an external operation (process termination) whose consequences depend on the argument (which app to stop). While not destructive in the data-loss sense, forcibly stopping an app can cause loss of unsaved work, corrupt application state, or disrupt critical services.

From the tool's definition Tool 'desktop_stop' performs the action 'Stop running desktop application' — actively terminates a process, which is an execution action with external side effects that cannot be predicted without knowing the target application.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs desktop_stop 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_stop, this is the rule to start with:

desktop_stop Rate-limited

desktop_stop 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "desktop_stop": {
      "limits": [
        {
          "counter": "desktop_stop_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Claude Mobile, apply this rule, and every desktop_stop call is checked against it from then on.

FAQ

Questions about desktop_stop

What does the desktop_stop tool do? +

Stop running desktop application. 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.

How do I enforce a policy on desktop_stop? +

Register the Claude Mobile MCP server in PolicyLayer and add a rule for desktop_stop: 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.

What risk level is desktop_stop? +

desktop_stop is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit desktop_stop? +

Yes. Add a rate_limit block to the desktop_stop 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.

How do I block desktop_stop completely? +

Set action: deny in the PolicyLayer policy for desktop_stop. 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.

What MCP server provides desktop_stop? +

desktop_stop 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.

KEEP EXPLORING

More on Claude Mobile, and thousands of servers like it.

This server

All 198 Claude Mobile tools → High-risk tools on this server →

Across the catalogue

stop_emba_scan on EMBA-MCP → All high-risk MCP tools → The MCP Attack Database →

Guides

Govern code and CI agents →Agent sandbox →Least privilege for MCP →