ADB MCP Server

Created By
srmoretea year ago
An MCP (Model Context Protocol) server for interacting with Android devices through ADB in TypeScript.
Overview

What is ADB MCP?

ADB MCP is a Model Context Protocol server designed for interacting with Android devices through ADB using TypeScript. It serves as a bridge between AI models and Android device functionalities.

How to use ADB MCP?

To use ADB MCP, clone the repository, install the dependencies, build the TypeScript code, and run the server using the command npx adb-mcp. Ensure that the server is running before using any ADB tools.

Key features of ADB MCP?

  • 📱 Device Management: List and interact with connected Android devices.
  • 📦 App Installation: Deploy APK files to connected devices.
  • 📋 Logging: Access device logs through logcat.
  • 🔄 File Transfer: Push and pull files between device and host.
  • 📸 UI Interaction: Capture screenshots and analyze UI hierarchy.
  • 🔧 Shell Command Execution: Run custom commands on the device.

Use cases of ADB MCP?

  1. Managing multiple Android devices for testing.
  2. Automating app installations and updates.
  3. Capturing UI screenshots for analysis.
  4. Executing shell commands for device management.

FAQ from ADB MCP?

  • Can ADB MCP work with any Android device?

Yes! ADB MCP is compatible with Android 8.0 and higher.

  • Is ADB MCP free to use?

Yes! ADB MCP is open-source and free to use under the MIT License.

  • What are the prerequisites for using ADB MCP?

You need Node.js (v16 or higher), ADB installed, and an Android device or emulator with USB debugging enabled.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
srmorete
Star
0
Language
JavaScript
License
MIT license

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago