The mobile-device-mcp server enables AI coding assistants to interact with mobile devices by providing tools for screenshots, UI inspection, touch interaction, and more. It enhances mobile development by allowing AI to see and manipulate the device directly.
From the registry: Control iOS and Android devices with multi-device and seamless Native/WebView support.
Please install the `mobile-device-mcp` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Node.js 18+** — Node 18 or newer
- **ADB** — Android SDK Platform Tools installed (https://developer.android.com/tools/releases/platform-tools)
Optional prerequisites:
- Google AI key (free tier) — Needed for AI visual analysis tools (https://aistudio.google.com/apikey)
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["-y","mobile-device-mcp"]
- optional environment variables:
- `GOOGLE_API_KEY`: Google API key for Gemini vision (required for AI tools, but server runs the 14 free tools without it) (example: `<your-google-api-key>`)
- `ANTHROPIC_API_KEY`: Anthropic API key for Claude vision (example: `<your-anthropic-api-key>`)
- `MOBILE_MCP_LICENSE_KEY`: Pro license key (example: `<your-license-key>`)
Note: 49 tools for Android/iOS device automation. Free tier has 14 tools, Pro unlocks AI vision + Flutter + iOS.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.GOOGLE_API_KEYrequiredGoogle API key for Gemini vision (recommended)Real-time infrastructure monitoring with metrics, logs, alerts, and ML-based anomaly detection.
Validate oh-my-posh configurations and segment snippets against the official schema.
Persistent codebase knowledge graph. Survives session restarts and context compaction.