Skip to main content
Glama

Launch App

mobile_launch_app
Destructive

Launch mobile apps on iOS or Android devices by specifying the package name, enabling automated app testing and interaction through the Mobile Next MCP server.

Instructions

Launch an app on mobile device. Use this to open a specific app. You can find the package name of the app by calling list_apps_on_device.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
deviceYesThe device identifier to use. Use mobile_list_available_devices to find which devices are available to you.
packageNameYesThe package name of the app to launch

Implementation Reference

  • src/server.ts:224-235 (registration)
    Registration of the mobile_launch_app tool, including schema definition and inline handler that validates input, requires a selected robot/device, calls robot.launchApp, and returns success message.
    tool(
    	"mobile_launch_app",
    	"Launch an app on mobile device. Use this to open a specific app. You can find the package name of the app by calling list_apps_on_device.",
    	{
    		packageName: z.string().describe("The package name of the app to launch"),
    	},
    	async ({ packageName }) => {
    		requireRobot();
    		await robot!.launchApp(packageName);
    		return `Launched app ${packageName}`;
    	}
    );
  • Inline handler function for mobile_launch_app tool: requires a device/robot to be selected, launches the app via robot.launchApp, returns confirmation.
    async ({ packageName }) => {
    	requireRobot();
    	await robot!.launchApp(packageName);
    	return `Launched app ${packageName}`;
    }
  • AndroidRobot.launchApp implementation: uses adb shell monkey to launch the app with LAUNCHER intent.
    public async launchApp(packageName: string): Promise<void> {
    	this.adb("shell", "monkey", "-p", packageName, "-c", "android.intent.category.LAUNCHER", "1");
    }
  • Simctl.launchApp (iPhone Simulator) implementation: uses xcrun simctl launch.
    public async launchApp(packageName: string) {
    	this.simctl("launch", this.simulatorUuid, packageName);
    }
  • IosRobot.launchApp implementation: asserts tunnel, uses go-ios launch command.
    public async launchApp(packageName: string): Promise<void> {
    	await this.assertTunnelRunning();
    	await this.ios("launch", packageName);
    }

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv1.0.0
    • removedInput schema / additionalProperties
      Removed value: -false
    • addedInput schema / properties / device
      Added value: +{
      +  "description": "The device identifier to use. Use mobile_list_available_devices to find which devices are available to you.",
      +  "type": "string"
      +}
    • changedInput schema / required
      Previous value: -[
      -  "packageName"
      -]New value: +[
      +  "device",
      +  "packageName"
      +]
  2. First observed

TDQS

A4.2/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotations include destructiveHint: true, indicating this is a mutation operation. The description adds context about needing a package name and how to obtain it, but doesn't elaborate on potential side effects (e.g., app state changes, permissions) or error conditions beyond what annotations imply. No contradiction with annotations exists.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the core purpose, followed by usage guidance in two concise sentences. Every sentence adds value without redundancy, making it efficient and easy to parse for an AI agent.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's moderate complexity (2 required parameters, destructive operation, no output schema), the description covers purpose, usage, and parameter sourcing adequately. It could improve by mentioning potential outcomes or errors, but annotations provide safety context, making it mostly complete for agent use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, with clear descriptions for both parameters. The description adds value by explaining that package names can be found via list_apps_on_device, providing practical guidance beyond the schema's technical definitions, but doesn't detail parameter interactions or constraints.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the specific action ('Launch an app') and resource ('on mobile device'), distinguishing it from sibling tools like mobile_install_app, mobile_terminate_app, and mobile_uninstall_app by focusing on opening rather than installing/removing apps. The mention of 'package name' further specifies the required identifier type.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly provides when to use this tool ('to open a specific app') and offers clear alternatives by referencing list_apps_on_device to find package names, though it doesn't explicitly state when not to use it. This guidance helps differentiate from other mobile tools like mobile_open_url or mobile_click_on_screen_at_coordinates.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.