How an AI agent can use Android apps that have no API (five routes in 2026)

Description and use

AI agents can interact with Android apps lacking public APIs by selecting from five routes—API/MCP, AppFunctions, Gemini in‑app tasks, local ADB frameworks, or cloud phones—each with specific prerequisites and constraints.

Problem

AI agents need to interact with Android apps that lack public APIs, such as food delivery, rides, banking, and other common phone apps.

Outcome

Agents can now automate tasks in a wide range of Android apps without APIs by selecting the appropriate route, balancing automation level with user involvement and platform constraints.

Workflow

• Identify the app and its available interaction route
• If the app publishes an API or MCP server, use it directly
• If the app supports Android AppFunctions and the agent is a system agent, call annotated functions
• If the app is supported by Gemini’s in-app tasks, let Gemini build the order and pause before the final action
• If using a local ADB-connected phone, run an observe-act loop with an accessibility-based framework
• If using a cloud phone, drive the phone via MCP, CLI or API and handle person‑required steps via live view

Evidence

In October 2026 there are five routes, and which one works depends on who you are and which app it is.

Source

AppFunctions is the clean future: apps annotate functions with @AppFunction, and agents call them directly, on the device.

Source

Gemini’s in-app tasks (beta since February 2026) can run multi-step tasks in DoorDash, Uber, Lyft, Instacart and a few others, in a virtual window on the phone.

Source

Accessibility-based agents like Mobilerun, mobile-use and AppAgent run an observe-act loop on a phone you connect over ADB.

Source