app_launch
Launch app by package name or bundle ID
This record as markdown: /tools/alexgladkov-claude-in-mobile/app-launch.md
What app_launch does on Claude Mobile
AI agents invoke app_launch 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 app_launch is rated High
Launching an application is an Execute category action because it triggers an external operation whose effects depend on arguments (which app to launch). While launching a benign app poses minimal risk, this tool could be exploited to launch malicious apps, background services, or apps that exfiltrate data.
From the tool's definition Tool description: 'Launch app by package name or bundle ID'. Server context indicates 'control devices with natural language through screenshots, UI interactions, text input, and app management.' The tool name and description explicitly perform an action…
Attacks that exploit this kind of access
The rule that runs app_launch 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 app_launch, this is the rule to start with:
app_launch 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 app_launch call is checked against it from then on.
Questions about app_launch
Launch app by package name or bundle ID. 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 app_launch: 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.
app_launch 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 app_launch 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 app_launch. 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.
app_launch 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