MCPgee
MCPgee
MCPgeeMCPgee

LAMDA

v1.0.0•Browser Automation•stable

The most powerful Android RPA agent framework, next generation mobile automation.

adbagentsaiandroidappium
Share:
7,802
Stars
0
Downloads
0
Weekly
0/5
View on GitHub

What is LAMDA?

LAMDA is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to most powerful android rpa agent framework, next generation mobile automation.

The most powerful Android RPA agent framework, next generation mobile automation.

This server falls under the Browser Automation category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • The most powerful Android RPA agent framework, next generati

Use Cases

Android automation
Device testing
firerpa

Maintainer

LicenseMIT
Languagepython
Versionv1.0.0
UpdatedMay 21, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux
View SourceBrowse All Servers

Installation

Manual Installation

npx lamda

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use LAMDA

FIRERPA (LAMDA) is a next-generation Android automation framework that runs as an on-device service and exposes 160+ APIs for UI automation, app control, OCR, image matching, file I/O, and dynamic analysis via Frida. It includes built-in MCP and agent tool-call support, making it possible to connect AI assistants to real Android devices or emulators for automated testing, RPA workflows, and security research. Developers and QA engineers use it to script complex mobile interactions and integrate device control into AI-driven agent pipelines.

Prerequisites

  • Android device or emulator running Android 6.0–16 with root access
  • Python 3.6+ on your host machine
  • ADB (Android Debug Bridge) installed and device connected
  • The FIRERPA APK installed and service running on the device (accessible at device-IP:65000)
  • An MCP-compatible client such as Claude Desktop or Cursor
1

Download and install the FIRERPA service APK on your Android device

Obtain the latest auto-run APK from the FIRERPA releases page and install it on your rooted Android device. Grant root access when prompted.

adb install firerpa.apk
2

Enable auto-start and reboot the device

Toggle the auto-start switch inside the FIRERPA app, then reboot. After restart, the service will be accessible on port 65000.

# If auto-start fails, start manually via ADB:
adb shell su root sh /data/server/bin/launch.sh
3

Verify the service is running

Open a browser or use curl to verify the FIRERPA service is reachable on your device's local IP at port 65000.

curl http://192.168.1.8:65000
4

Install the Python SDK on your host machine

Install the lamda Python client library to control the device from your host machine over the network.

pip install lamda
5

Connect to the device and run a basic automation

Use the Python SDK to connect to the FIRERPA service and perform a UI action such as launching an app or tapping a UI element.

from lamda.client import Device

d = Device("192.168.1.8")
d.start_app("com.example.myapp")
d.tap(500, 800)
6

Configure Claude Desktop to use LAMDA MCP tools

Add the LAMDA MCP server entry to your Claude Desktop configuration so AI agents can call device automation tools directly.

LAMDA Examples

Client configuration

Claude Desktop config to launch the LAMDA MCP server via npx.

{
  "mcpServers": {
    "lamda": {
      "command": "npx",
      "args": ["lamda"],
      "env": {
        "LAMDA_DEVICE_IP": "192.168.1.8"
      }
    }
  }
}

Prompts to try

Example tasks you can ask an AI agent with LAMDA connected to your Android device.

- "Open the Settings app on my Android device and take a screenshot"
- "Scroll through the contacts list and find the entry named John Doe"
- "Run a Frida script to analyze the network calls made by com.example.app"
- "Install the APK from /sdcard/Downloads/test.apk and launch it"
- "Use OCR to read the text on the current screen and return it as JSON"

Troubleshooting LAMDA

Cannot connect to the FIRERPA service at device-IP:65000

Ensure the device and host machine are on the same network. If auto-start failed, manually run: `adb shell su root sh /data/server/bin/launch.sh`. Check that the device firewall is not blocking port 65000.

Root access denied when starting the FIRERPA service

Open the FIRERPA app on the device and confirm root permission was granted in your root manager (Magisk, SuperSU, etc.). The service requires persistent root to function.

Python SDK raises ConnectionRefusedError

Verify the device IP is correct with `adb shell ip addr`. Ensure the FIRERPA service is running by checking port 65000 with `adb shell netstat -tlnp | grep 65000`.

Frequently Asked Questions about LAMDA

What is LAMDA?

LAMDA is a Model Context Protocol (MCP) server that most powerful android rpa agent framework, next generation mobile automation. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install LAMDA?

Follow the installation instructions on the LAMDA GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with LAMDA?

LAMDA works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is LAMDA free to use?

Yes, LAMDA is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Learn More About MCP Servers

Getting Started with MCP

Set up your first MCP server in minutes

MCP Setup Guide

Configure MCP in Claude, Cursor & VS Code

All MCP Tutorials

18+ hands-on guides for developers

MCP FAQ

40+ answers about Model Context Protocol

LAMDA Alternatives — Similar Browser Automation Servers

Looking for alternatives to LAMDA? Here are other popular browser automation servers you can use with Claude, Cursor, and VS Code.

Chrome DevTools MCP

★ 40.6k

AI-powered Chrome automation server with natural language element detection. Control Chrome browser through MCP protocol for testing, debugging, and performance analysis. Features 91% accuracy in element location, works with free AI models, and suppo

UI TARS Desktop

★ 34.9k

📇 🏠 - Browser automation capabilities using Puppeteer, both support local and remote browser connection.

Playwright

★ 32.8k

A production-ready browser automation server that enables AI assistants to interact with web pages using tools for navigation, element interaction, and data extraction. It features a built-in Inspector UI and robust crash recovery for reliable automa

Page Agent

★ 18.0k

JavaScript in-page GUI agent. Control web interfaces with natural language.

Chrome

★ 11.7k

An extension-based MCP server that enables AI assistants to control your browser, leveraging existing sessions and login states for automation and content analysis. It provides over 20 tools for semantic tab search, interactive element manipulation,

Browser Tools MCP

★ 7.2k

This application is a powerful browser monitoring and interaction tool that enables AI-powered applications via Anthropic's Model Context Protocol (MCP) to capture and analyze browser data through a Chrome extension.

Browse More Browser Automation MCP Servers

Explore all browser automation servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Browser AutomationBrowse All Servers

Quick Config Preview

{ "mcpServers": { "lamda": { "command": "npx", "args": ["-y", "lamda"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use LAMDA?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides
Explore All ServersRead Our Guides