rn-device-mcp

Overview Schema Source Related Servers Discussions Admin

Install an APK

android_install_apk

Installs or reinstalls an Android APK on a connected device or emulator while keeping existing app data; specify a serial only when multiple devices are online.

Instructions

Installs (or reinstalls, keeping data) an APK.

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": {
      "apkPath": "<apkPath>"
    },
    "name": "android_install_apk"
  }
}

Input Schema

Name	Required	Description	Default
`serial`	No	adb serial (from android_devices). Default: the only online device.
`apkPath`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 4, 2026

TDQS

C2.9/5.0

Behavior3/5

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

The annotations already declare readOnlyHint=false and destructiveHint=false, so the mutation-vs-read question is settled structurally. The description adds real value by noting the reinstall path preserves existing app data — a behavior not derivable from annotations. It stops short of stating failure modes (no device connected, invalid path) or whether the app is started after install.

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

Conciseness4/5

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

A single front-loaded sentence with no filler; the reinstalls-keep-data caveat is placed where it is immediately visible. It is efficiently worded, though the brevity contributes to the missing guidance noted elsewhere.

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

Completeness2/5

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

For a two-parameter mutation tool with no output schema and incomplete parameter documentation, the description should at least clarify the apkPath semantics and the device-selection precondition. As written, an agent must guess what apkPath refers to and whether the install launches the app.

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

Parameters2/5

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

Schema coverage is 50%: the serial parameter is documented in the schema, but apkPath carries only minLength:1 with no explanation. The description does not say whether apkPath is a host filesystem path or a device path, nor what formats are accepted, so the single undocumented required parameter is left ambiguous.

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?

"Installs (or reinstalls, keeping data) an APK" gives a specific verb and resource, so the core action is unambiguous. It does not distinguish itself from the related iOS sibling (ios_install_app) or clarify how it relates to android_launch_app, but the verb+object pairing is clear enough to select on.

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

Usage Guidelines2/5

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

There is no when-to-use or when-not-to-use guidance: nothing about needing a booted/online device, no mention that the app is not launched afterwards (use android_launch_app), and no alternative tool named. The parenthetical about reinstalling is the only context offered.

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