# io.github.MobAI-App/mobai-mcp (npm · mobai-mcp)

AI-powered mobile device automation for Android and iOS devices, emulators, and simulators

- Trust score: 71/100 (medium)
- Change this week: +18
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `mobai-mcp`: 71/100 (this document), [markdown](https://verifymcp.io/servers/mobai-app-mobai-mcp/mobai-mcp.md), [page](https://verifymcp.io/servers/mobai-app-mobai-mcp/mobai-mcp)

## Channel facts

- Registry: `npm`
- Package: `mobai-mcp`
- Version: `1.2.1`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Supply Chain Security**: 86/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (94 of 98), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (94 of 98), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (Apache-2.0).
  - Actively maintained (last published 22 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 87/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 1393 tokens (~53/item across 26 items; 22 tools + 4 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add mobai-app-mobai-mcp -- npx -y mobai-mcp
```

### Codex

```bash
codex mcp add mobai-app-mobai-mcp -- npx -y mobai-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "mobai-app-mobai-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "mobai-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add mobai-app-mobai-mcp --command npx --arg -y --arg mobai-mcp
```

### Hermes

```yaml
mcp_servers:
  mobai-app-mobai-mcp:
    command: "npx"
    args: ["-y", "mobai-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "mobai-app-mobai-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "mobai-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-02 (score 71, +45)

- [security regression] Provenance: unverified → fail
- [security improvement] Install scripts: unverified → pass
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Malware scan: unverified → pass
- [functional regression] Security disclosure: fail → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Schema quality: 100 → unverified
- [functional improvement] Schema quality: unverified → excellent
- [functional improvement] License: unverified → pass
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Stability: unverified → 0.23
- [functional improvement] Dependency health: unverified → partial
- [functional] Licence: Apache-2.0

### 2026-07-31 (score 26, −27)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-28 (score 53, 0)

- [functional regression] Security disclosure: unverified → fail

### 2026-07-27 (score 53)

First indexed and scored.

## MCP tools (22)

### `list_devices` (~24 tokens)

List all connected Android and iOS devices, emulators, and simulators

### `get_device` (~35 tokens)

Get information about a specific device

Input parameters:

- `device_id` (string, required): Device ID (serial for Android, UDID for iOS)

### `start_bridge` (~41 tokens)

Start the on-device bridge (accessibility service on Android, WebDriverAgent on iOS). Required before automation.

Input parameters:

- `device_id` (string, required): Device ID

### `stop_bridge` (~24 tokens)

Stop the on-device bridge

Input parameters:

- `device_id` (string, required): Device ID

### `get_screenshot` (~35 tokens)

Capture a screenshot from the device. Returns the file path to the saved PNG.

Input parameters:

- `device_id` (string, required): Device ID

### `get_ui_tree` (~93 tokens)

Get the UI accessibility tree showing all visible elements with indices for tapping

Input parameters:

- `device_id` (string, required): Device ID
- `include_keyboard` (boolean): Include keyboard elements in the tree (default: false). Useful for interacting with on-screen keyboards.
- `only_visible` (boolean): Filter to only visible elements (default: true)
- `verbose` (boolean): Include detailed elements array with bounds (default: false)

### `tap` (~76 tokens)

Tap an element by index (from UI tree) or coordinates

Input parameters:

- `device_id` (string, required): Device ID
- `index` (number): Element index from UI tree (preferred)
- `x` (number): X coordinate (use with y instead of index)
- `y` (number): Y coordinate (use with x instead of index)

### `type_text` (~41 tokens)

Type text on the device (tap input field first to focus)

Input parameters:

- `device_id` (string, required): Device ID
- `text` (string, required): Text to type

### `swipe` (~82 tokens)

Perform a swipe gesture

Input parameters:

- `device_id` (string, required): Device ID
- `duration_ms` (number): Duration in milliseconds (default: 300)
- `from_x` (number, required): Starting X coordinate
- `from_y` (number, required): Starting Y coordinate
- `to_x` (number, required): Ending X coordinate
- `to_y` (number, required): Ending Y coordinate

### `go_home` (~24 tokens)

Navigate to device home screen

Input parameters:

- `device_id` (string, required): Device ID

### `launch_app` (~48 tokens)

Launch an application by bundle ID

Input parameters:

- `bundle_id` (string, required): App bundle ID (e.g., com.apple.Preferences, com.android.settings)
- `device_id` (string, required): Device ID

### `list_apps` (~25 tokens)

List installed applications on the device

Input parameters:

- `device_id` (string, required): Device ID

### `get_ocr` (~46 tokens)

Perform OCR text recognition on the current screen (iOS only). Returns detected text with screen coordinates for tapping (already adjusted for tapping).

Input parameters:

- `device_id` (string, required): Device ID

### `execute_dsl` (~219 tokens)

Execute a batch of automation steps using the DSL (Domain Specific Language).
This is the PREFERRED method for complex automation as it's more reliable than sequential API calls.

DSL supports: observe, tap, type, toggle, swipe, scroll, open_app, navigate, wait_for, assert_*, if_exists, delay, execute_js (web)

Example DSL script:
{
  "version": "0.2",
  "steps": [
    {"action": "observe", "context": "native", "include": ["ui_tree"]},
    {"action": "tap", "predicate": {"text_contains": "Settings"}},
    {"action": "delay", "duration_ms": 500},
    {"action": "observe", "context": "native", "include": ["ui_tree"]}
  ],
  "on_fail": {"strategy": "retry", "max_retries": 2}
}

Input parameters:

- `device_id` (string, required): Device ID
- `script` (object, required): DSL script object with version, steps, and optional on_fail

### `run_agent` (~101 tokens)

Run an AI agent to perform a task autonomously. The agent will observe the screen, make decisions, and execute actions to complete the task.

Input parameters:

- `agent_type` (string): Agent type (default: toolagent)
- `device_id` (string, required): Device ID
- `task` (string, required): Task description (e.g., 'Open Settings and enable WiFi')
- `use_vision` (boolean): Enable vision/screenshots (default: from app settings)

### `web_list_pages` (~34 tokens)

List available web pages (browser tabs and WebViews) for web automation

Input parameters:

- `device_id` (string, required): Device ID

### `web_navigate` (~38 tokens)

Navigate to a URL in the browser

Input parameters:

- `device_id` (string, required): Device ID
- `url` (string, required): URL to navigate to

### `web_get_dom` (~29 tokens)

Get the DOM tree of the current web page

Input parameters:

- `device_id` (string, required): Device ID

### `web_click` (~49 tokens)

Click an element in the web page using CSS selector

Input parameters:

- `device_id` (string, required): Device ID
- `selector` (string, required): CSS selector (e.g., 'button.submit', '#login-btn')

### `web_type` (~51 tokens)

Type text into a web element using CSS selector

Input parameters:

- `device_id` (string, required): Device ID
- `selector` (string, required): CSS selector for the input element
- `text` (string, required): Text to type

### `web_execute_js` (~47 tokens)

Execute JavaScript in the web page context

Input parameters:

- `device_id` (string, required): Device ID
- `script` (string, required): JavaScript code to execute (use 'return' for results)

### `http_request` (~172 tokens)

Make a raw HTTP request to the MobAI API. Use this for advanced operations not covered by other tools.

Base URL: http://127.0.0.1:8686/api/v1

Common endpoints:
\- GET /devices - List devices
\- GET /devices/{id}/screenshot - Take screenshot
\- GET /devices/{id}/ui-tree - Get UI tree
\- POST /devices/{id}/dsl/execute - Execute DSL script
\- POST /devices/{id}/agent/run - Run AI agent

Input parameters:

- `body` (string): Request body as JSON string
- `method` (string, required): HTTP method
- `timeout_ms` (number): Timeout in milliseconds (default: 600000)
- `url` (string, required): Full URL or endpoint path (e.g., /devices)

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/mobai-app-mobai-mcp/mobai-mcp#diagnostics

## Score history

- 2026-08-03: 71
- 2026-08-02: 71
- 2026-08-01: 26
- 2026-07-31: 26
- 2026-07-30: 53
- 2026-07-28: 53
- 2026-07-27: 53

## Links

- npm package: https://www.npmjs.com/package/mobai-mcp
- Socket report: https://socket.dev/npm/package/mobai-mcp
- Repository: https://github.com/MobAI-App/mobai-mcp
- Changelog RSS feed: https://verifymcp.io/servers/mobai-app-mobai-mcp/mobai-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/mobai-app-mobai-mcp/mobai-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/mobai-app-mobai-mcp/mobai-mcp