Bridge AI and Android devices using Android Debug Bridge for Windows. Manage devices, run shell commands, and install ap
Add new capabilities to Claude beyond text generation
Example: Access external data sources, execute code, interact with tools and services
Transform Claude from chatbot to action-taking agent
Provide Claude with access to relevant context and data
Example: Load project documentation, access knowledge bases, query databases
Get more accurate, context-aware responses
Automate multi-step workflows combining AI and external tools
Example: Research → Summarize → Create document → Send notification
Complete complex tasks end-to-end without manual steps
Time estimate: 15-60 minutes depending on server complexity
Prerequisites
Loops
Run Loops with Claude
YouTrack
Plan and track work in YouTrack
Ample Computer
Deploy apps, databases and storage from Claude and get a live URL, with no servers or cloud console to set up.
iubenda: Privacy policy & cookie banner
GDPR and CCPA compliance: cookie consent, cookie scanner, and terms and conditions
JupiterOne
Ask questions about your JupiterOne agentic security and it asset graph and manage alerts, rules, and dashboards — in natural language.
Unstructured Transform
ADB (Android Debug Bridge) has been reliable for tool-calling workflows; the MCP profile page is a good permalink for internal docs.
ADB (Android Debug Bridge) is a well-scoped MCP server in the explainx.ai directory — install snippets and categories matched our Claude Code setup.
We wired ADB (Android Debug Bridge) into a staging workspace; the listing’s GitHub and npm pointers saved time versus hunting across READMEs.
According to our notes, ADB (Android Debug Bridge) benefits from clear Model Context Protocol framing — fewer ambiguous “AI plugin” claims.
Useful MCP listing: ADB (Android Debug Bridge) is the kind of server we cite when onboarding engineers to host + tool permissions.
We wired ADB (Android Debug Bridge) into a staging workspace; the listing’s GitHub and npm pointers saved time versus hunting across READMEs.
ADB (Android Debug Bridge) is a well-scoped MCP server in the explainx.ai directory — install snippets and categories matched our Claude Code setup.
ADB (Android Debug Bridge) has been reliable for tool-calling workflows; the MCP profile page is a good permalink for internal docs.
According to our notes, ADB (Android Debug Bridge) benefits from clear Model Context Protocol framing — fewer ambiguous “AI plugin” claims.
ADB (Android Debug Bridge) has been reliable for tool-calling workflows; the MCP profile page is a good permalink for internal docs.
showing 1-10 of 51
Share your MCP server with the developer community
Select a client to integrate this server.
Claude Desktop configuration
{
"mcpServers": {
"adb": {
"command": "npx",
"args": [
"adb-mcp"
]
}
}
}Bridges AI with Android devices through ADB, enabling device management, shell commands, app installation, file transfers, and UI inspection without requiring direct ADB knowledge.
ADB (Android Debug Bridge) is a community-built MCP server published by srmorete that provides AI assistants with tools and capabilities via the Model Context Protocol. Bridge AI and Android devices using Android Debug Bridge for Windows. Manage devices, run shell commands, and install ap It is categorized under developer tools. This server exposes 8 tools that AI clients can invoke during conversations and coding sessions.
You can install ADB (Android Debug Bridge) in your AI client of choice. Use the install panel on this page to get one-click setup for Cursor, Claude Desktop, VS Code, and other MCP-compatible clients. This server runs locally on your machine via the stdio transport.
An MCP (Model Context Protocol) server for interacting with Android devices through ADB. This TypeScript-based tool provides a bridge between AI models and Android device functionality.
To install ADB Android Device Server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @srmorete/adb-mcp --client claude
# Clone the repository
git clone https://github.com/srmorete/adb-mcp.git
cd adb-mcp
# Install dependencies
npm install
# Build the TypeScript code
npm run build
# Run the server
npx adb-mcp
The server uses default ADB paths. For custom ADB location:
export ADB_PATH=/path/to/adb
npx adb-mcp
Add the ADB MCP server configuration:
{
"mcpServers": {
"adb": {
"command": "npx",
"args": [
"adb-mcp"
]
}
}
}
IMPORTANT: The server must be running before using any ADB tools.
Start the server using:
npx adb-mcp
You should see:
[INFO] ADB MCP Server connected and ready
Keep this terminal window open while using the ADB tools.
All tools are available with the following naming convention:
adb_devices - List connected devicesadb_shell - Execute shell commands on a deviceadb_install - Install an APK file using a local file pathadb_package_manager - Execute Package Manager (pm) commands - list packages, grant/revoke permissions, manage appsadb_activity_manager - Execute Activity Manager (am) commands - start activities, broadcast intents, control app behavioradb_logcat - View device logs with optional filteringadb_pull - Pull files from a deviceadb_push - Push files to a devicedump_image - Take a screenshot of the current screeninspect_ui - Get UI hierarchy in XML format (most useful for AI interaction)If tools aren't working:
Server Issues:
npx adb-mcp)LOG_LEVEL=3 npx adb-mcpps aux | grep "adb-mcp" | grep -v grepkill -9 [PID]Device Connection:
adb_devicesadb kill-server && adb start-serverADB Issues:
adb versionDevice Setup:
vibe-coded so if you spot some weird stuff... well now you know 🙂This project is licensed under the MIT License - see the LICENSE file for details.
Steps
Troubleshooting
✓ Do
✗ Don't
💡 Pro Tips
Architecture
Model Context Protocol standardizes how AI hosts (Claude, Cursor) communicate with external tools and data sources through server implementations.
Protocols
Compatibility
✓ Use when
Use when you need Claude to access external data, execute actions, or integrate with tools. Best for extending AI capabilities beyond conversation.
✗ Avoid when
Avoid when native integrations exist (use official APIs directly), for real-time critical systems, or when security/compliance requires zero external dependencies.
Turn any document into AI-ready structured data