rn-device-mcp

by Artem-Pavlenko

Overview Schema Source Related Servers Discussions Admin

TypeScript

Local

Launch an app

ios_launch_app

Launch an installed iOS app by bundle ID on a simulator, with optional relaunch to terminate it first for a cold start.

Instructions

Launches an installed app by bundle id. relaunch: true terminates it first (cold start).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "bundleId": "<bundleId>"
    },
    "name": "ios_launch_app"
  }
}

Input Schema

Name	Required	Description
`device`	No	Simulator udid or name. Default "booted" (the running simulator).
`bundleId`	Yes
`relaunch`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 4, 2026

TDQS

A3.9/5.0

Behavior4/5

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

Annotations only declare readOnlyHint=false and destructiveHint=false; the description adds the important detail that relaunch: true terminates the app first, which is behavior an agent could otherwise trigger blindly. It omits what happens if the app is not installed or whether a running instance is foregrounded by default, but the key side effect is disclosed.

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?

Two short sentences, front-loaded with the core action and identifier, followed immediately by the one non-obvious flag. No filler or redundant restatement of the title.

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?

For a three-parameter tool with no output schema, the description covers the action, the required identifier, and the significant side-effecting flag. Missing only failure-mode behavior (app not installed, launch errors), which is a minor gap.

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

Parameters4/5

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

Schema coverage is only 33% (device is the sole documented param), so the description must carry weight and does: it defines bundleId as the lookup key and fully specifies relaunch as terminate-then-start. The device parameter is left to the schema, which does describe it, so the combined coverage is adequate.

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

Purpose4/5

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

States a specific verb (launches) and resource (an installed app) plus the identifier form (bundle id), which distinguishes it from ios_open_url and ios_terminate_app. It does not explicitly name the Android counterpart or state exclusions, keeping it at 4 rather than 5.

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

Usage Guidelines3/5

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

The phrase 'installed app' implies a precondition (use ios_install_app first) and the relaunch flag defines a cold-start variant, so usage is partially inferable. There is no explicit when-to-use/when-not guidance versus siblings like ios_open_url or ios_boot.

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