npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

@mobileai/mcp-server

v1.0.1

Published

MCP bridge server for @mobileai/react-native — connect AI editors to your React Native app

Readme

@mobileai/mcp-server

The Model Context Protocol (MCP) bridge for React Native. Connect any AI (like Claude Desktop or Google Antigravity) to your React Native app.

This is the companion MCP server for the @mobileai/react-native (or react-native-agentic-ai) package.

It acts as a local proxy that translates standard MCP traffic (from AI editors/agents) into WebSockets that communicate directly with your running React Native app (iOS/Android emulator or physical device).


⚡ What this enables

  1. AI-Powered UI Testing: Connect an AI to your emulator and ask it to "verify the checkout flow" in English. The AI will read your live app UI, tap buttons, fill forms, and report bugs — without writing any test code.
  2. App Remote Control: Let autonomous agents interact with your live app to scrape data, navigate screens, or perform automated tasks.

🚀 Quick Setup

1. Start the MCP Server

You don't even need to install it. Just run it via npx:

npx @mobileai/mcp-server

(By default, it listens on port 3100 for HTTP/SSE MCP traffic, and port 3101 for the React Native WebSocket).

2. Connect Your React Native App

In your app, pass the mcpServerUrl prop to your <AIAgent>:

import { AIAgent } from '@mobileai/react-native';

export default function App() {
  return (
    <AIAgent 
      mcpServerUrl="ws://localhost:3101" 
      apiKey="YOUR_API_KEY"
      navRef={navRef}
    >
      {/* Your app components */}
    </AIAgent>
  );
}

3. Connect Your AI Client

Configure your AI tool to connect to the MCP server:

Google Antigravity: Add to ~/.gemini/antigravity/mcp_config.json:

{
  "mcpServers": {
    "mobile-app": {
      "command": "npx",
      "args": ["@mobileai/mcp-server"]
    }
  }
}

Claude Desktop: Add to claude_desktop_config.json:

{
  "mcpServers": {
    "mobile-app": {
      "url": "http://localhost:3100/mcp/sse"
    }
  }
}

(Once connected, the AI will automatically discover the tools execute_task and get_app_status to interact with your app).


⚙️ Configuration (Environment Variables)

You can customize the ports by setting environment variables before running the server:

| Variable | Default | Description | |----------|---------|-------------| | MCP_PORT | 3100 | HTTP port that AI clients (Claude, Antigravity) connect to | | WS_PORT | 3101 | WebSocket port that your React Native app connects to |

Example:

MCP_PORT=8080 WS_PORT=8081 npx @mobileai/mcp-server

🔗 Links