Launch

SERVERAndroid SOURCE@midscene/android-mcp

High RISK CLASS

Category Execute

Parameters 71 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/android/launch.md

WHAT IT DOES

What Launch does on Android

AI agents invoke Launch to trigger actions in Android. 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.

Parameter	Type	Required	Description
`uri`	string	Yes	App name, package name, or URL to launch. Prioritize using the exact package name or URL the user has provided. If none provided, use the accurate app name.
`android.deviceId`	string	—	Android device ID (from adb devices)
`android.useScrcpy`	boolean	—	Enable scrcpy accelerated screenshots
`android.aiActContext`	string	—	Background knowledge passed to aiAct. Default: no extra context.
`android.waitAfterAction`	number	—	Wait time in milliseconds after each action execution. Default: 300ms.
`android.replanningCycleLimit`	integer	—	Maximum number of replanning cycles for aiAct. Default: model adapter default.
`android.screenshotShrinkFactor`	number	—	Screenshot shrink factor before sending images to AI. Default: 1; high values may reduce recognition quality, especially on mobile.

Parameters from the server's own tool schema.

RISK

Why Launch is rated High

This tool triggers external operations (app launches, URL navigation) that can have unpredictable side effects depending on what URI an AI agent provides. While not as severe as destructive operations, launching arbitrary apps or URLs could lead to unintended consequences like accessing sensitive applications, triggering unwanted network requests, or invoking apps with security implications.

From the tool's definition Tool description states 'Launch an Android app or URL' with parameter 'uri' that accepts 'App name, package name, or URL to launch'.

Risk signalsAccepts URL/endpoint input (uri)

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs Launch safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Android, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For Launch, this is the rule to start with:

Launch Rate-limited

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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "Launch": {
      "limits": [
        {
          "counter": "launch_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 Android, apply this rule, and every Launch call is checked against it from then on.

FAQ

Questions about Launch

What does the Launch tool do? +

Launch action, Launch an Android app or URL. Parameters: uri (string) - App name, package name, or URL to launch. Prioritize using the exact package name or URL the user has provided. If none provided, use the accurate app name. It is categorised as a Execute tool in the Android MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

What parameters does Launch accept? +

Launch accepts 7 parameters: uri, android.deviceId, android.useScrcpy, android.aiActContext, android.waitAfterAction, android.replanningCycleLimit, android.screenshotShrinkFactor. Required: uri. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on Launch? +

Register the Android MCP server in PolicyLayer and add a rule for 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 Android. Nothing to install.

What risk level is Launch? +

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

Can I rate-limit Launch? +

Yes. Add a rate_limit block to the 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.

How do I block Launch completely? +

Set action: deny in the PolicyLayer policy for 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.

What MCP server provides Launch? +

Launch is provided by the Android MCP server (@midscene/android-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Android, and thousands of servers like it.

This server

All 23 Android tools → High-risk tools on this server →

Across the catalogue

All high-risk MCP tools → The MCP Attack Database →

Guides

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