Advertise
MCP.so
Sign In

MCP ADB

@isseikz

Repository

Basic information

Category

Other

Transports

stdio

Author

isseikz

About MCP ADB

MCP (Model Context Protocol) Server to control Android TV

MCP ADB config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "mcp-adb": {
      "command": "node",
      "args": [
        "/path/to/mcp-adb/build/index.js"
      ],
      "env": {
        "ADB_PATH": "/path/to/adb"
      }
    }
  }
}

MCP ADB tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is MCP-ADB?

MCP-ADB is a Model Context Protocol (MCP) server that integrates with Android Debug Bridge (ADB) to allow AI assistants to interact with connected Android devices. It is intended for developers and users who want to control Android devices programmatically through an AI assistant.

How to use MCP-ADB?

Clone the repository, install dependencies with npm install, and build the project with npm run build. Then configure the MCP server in Claude Desktop’s claude_desktop_config.json by specifying the path to the built index.js file and optionally the ADB_PATH environment variable. Use the provided tools (screenshot, pressKey) and access resources (adb://devices, adb://screenshots/{filename}) to interact with Android devices.

Key features of MCP-ADB

  • Capture screenshots from connected Android devices with automatic resizing
  • Return screenshot data as base64-encoded PNG strings
  • Send key events (navigation, back, home) to Android devices
  • Target specific devices when multiple devices are connected
  • List all connected Android devices via resource URIs
  • Access screenshots and device information through resource URIs

Use cases of MCP-ADB

  • Take a screenshot of an Android device and use AI to analyze its content
  • Send navigation commands (DPAD, back, home) to automate device interaction
  • List all connected Android devices to manage multi-device setups
  • Retrieve a stored screenshot by filename for later processing

Frequently asked questions

1

What does MCP-ADB do?

MCP-ADB provides an MCP server that connects an AI assistant to Android devices via ADB, enabling screenshot capture, key event simulation, and device listing.

2

What are the prerequisites for MCP-ADB?

You need Node.js (v16 or higher), ADB installed and available in PATH (or set via the ADB_PATH environment variable), and connected Android device(s) with USB debugging enabled.

3

How do I install MCP-ADB?

Clone the repository, then run `npm install` and `npm run build` to compile the TypeScript code to JavaScript in the `build` directory.

4

How do I configure MCP-ADB with Claude Desktop?

Edit `claude_desktop_config.json` (found in Claude Desktop’s installation directory or via Settings → Developer → Edit Config) and add an entry under `mcpServers` with the command `node` and args pointing to the built `index.js` file, plus an optional `ADB_PATH` environment variable.

5

What tools are available in MCP-ADB?

Two tools: `screenshot` captures a screenshot (optionally targeting a device by ID) and returns base64 image data; `pressKey` sends a key event (e.g., KEYCODE_DPAD_DOWN, KEYCODE_BACK) to a device.

Comments

More Other MCP servers

Activepieces

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

23.2K

Maestro

mobile-dev-inc

Painless E2E Automation for Mobile and Web

14.8K

Reactive Resume

amruthpillai

A one-of-a-kind resume builder that keeps your privacy in mind. Completely secure, customizable, portable, open-source and free forever. Try it out today!

39.5K

Handl

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.

Hindsight

vectorize-io

Hindsight: Agent Memory That Learns

50.4K
Advertise