An MCP server based on MaaFramework, providing Android device and Windows desktop automation capabilities for AI assistants, supporting operations such as OCR recognition, clicking, swiping, and text input, and capable of converting operation processes into reusable Pipelines.

DroidMind is a bridge tool for controlling Android devices via AI, implementing the Model Context Protocol (MCP), allowing AI to interact securely with Android devices through natural language.

Jenius is a general multi - agent AI Agent that enables remote control of smart home devices by integrating Home Assistant and supports the access of multiple Mi Home devices.

An MCP server that connects AI assistants with the LedFX lighting control system, controls LED lighting effects, manages devices, creates scenes and color palettes through natural language, and supports AI-driven scene recommendations and function explanations.

An offline documentation MCP server for Garmin Connect IQ SDK, providing complete access to version 8.2.3 documentation for AI assistants, including API documentation, programming guides, device references, and troubleshooting resources.

FridaC2MCP is a proof - of - concept project that exposes the capabilities of the Frida dynamic instrumentation tool as a remote MCP server through HTTP streaming, aiming to achieve remote and automated mobile application security testing. The project is designed to run on a rooted Android device, allowing clients to analyze and manipulate running applications over the network.

mcp2mqtt is a bridge project that connects IoT devices with large AI models, enabling natural language control of hardware devices through the MCP and MQTT protocols.

native-devtools-mcp is a cross-platform MCP server that provides AI agents with the ability to automate control of macOS, Windows, and Android systems, including screenshot, OCR text recognition, simulated click input, window management, and Android device control.

An MCP server that runs natively on the Hubitat smart home hub, allowing AI assistants to control devices, create automation rules, and manage the system through natural language. It provides 69 tools and a built - in rule engine.

A Model Context Protocol (MCP) integration tool for controlling Home Assistant devices through an AI assistant, supporting device search, on/off control, and light color and brightness adjustment.

RegenNexus UAP is a universal adapter protocol for connecting devices, robots, applications, and AI agents, providing low-latency, high-security communication, and supporting multiple hardware and MCP integrations.

A professional serial communication MCP server that provides AI assistants with comprehensive serial communication capabilities, supports embedded systems, IoT devices, and hardware debugging, and has cross - platform support and multiple data format processing functions.

The TagoIO MCP Server is a tool that allows AI models to directly interact with the TagoIO IoT platform, providing functions such as device management, data analysis, platform integration, and code generation to enhance the development workflow and intelligent data analysis.

MCP2Serial is a bridge project connecting physical devices with large AI models, enabling intelligent control of the Internet of Things by controlling hardware devices through natural language.

The Sauce Labs MCP Server is a model context protocol server fully integrated with the Sauce Labs testing platform, supporting AI assistants to manage the device cloud, test tasks, build analysis, and monitor the test infrastructure through natural language interaction.

Home Assistant MCP is a standardized protocol server that provides a secure and typed interface for AI assistants to interact with the smart home system, supporting device control, status query, and automated management.

HASS-MCP is an MCP server developed in Go language that exposes the functions of the Home Assistant smart home system to AI assistants, supporting AI clients such as Claude and Cursor to control and manage smart home devices via the Model Context Protocol.

The Shodan MCP Server is a model context protocol server that provides Shodan API functionality, allowing AI assistants to query detailed information about Internet - connected devices and services.

mcp2tcp is a bridge project connecting physical hardware and large AI models, realizing natural - language control of hardware devices through the MCP protocol.

The MCP Mobile Server is an AI-driven mobile development toolset that provides 36 powerful Flutter, Android, and iOS development tools for MCP clients such as Claude Desktop, including intelligent device management, automated builds, and cross-platform deployment features, significantly improving mobile development efficiency.

This project is a Bluetooth device detection server based on the MCP protocol. It supports cross - platform scanning and identification of Bluetooth devices and provides an API interface for AI assistants to call.

An automated MCP service for Android devices built on Open - AutoGLM. It connects to the phone via ADB and invokes the visual model, and can access Xiaozhi AI for intelligent control.

Mitto is a modern AI programming assistant management platform that supports connecting multiple ACP - compatible AI coding agents, providing a native macOS application, a web interface, and a CLI for cross - device session management and real - time collaboration.

An MCP server that enables interaction between the AI assistant and Android devices via ADB

An MCP server for SwitchBot device control, providing smart home device management functions for AI assistants

Hass-MCP is a protocol server that connects Home Assistant with AI assistants (such as Claude), enabling querying, controlling, and automating management of smart home devices.

The openwrt-mcp-server is a lightweight and scalable MCP protocol server designed for OpenWrt embedded devices. It supports both MQTT and HTTP protocols, enabling two-way JSON-RPC communication between devices and AI systems, with security authentication and a modular architecture.

The ThingsBoard MCP Server is a service that provides a natural language interface for LLMs and AI agents, allowing interaction with the ThingsBoard IoT platform through natural language commands to achieve functions such as device management, data query, and analysis.

The MobAI MCP server is a Model Context Protocol service for mobile device automation. It connects the MobAI desktop application through an HTTP API, enabling AI programming assistants to control Android and iOS devices and emulators, achieving UI automation, web operations, and batch script execution.

BeeMCP is an unofficial MCP server used to connect the data of Bee wearable devices with large - language models (such as Claude), enabling AI assistants to access and manipulate users' personal data, including conversations, fact records, to - do lists, and location history.

The Enhanced Home Assistant MCP Server provides comprehensive integration with smart home devices, automation, and system management, enabling AI assistants to control devices such as lights, climate systems, and media players, and supporting automation management and system monitoring.

A stateful Bluetooth Low Energy (BLE) Model Context Protocol (MCP) server that provides development tools and AI agents with the ability to interact with real BLE hardware. It supports operations such as scanning, connecting, reading and writing, and subscribing to notifications, and can extend device protocol specifications and plugins.

Android-MCP is a lightweight open-source project that serves as a bridge between AI agents and Android devices. It enables real-world task operations such as app navigation, UI interaction, and automated testing through the MCP server, without relying on traditional computer vision or pre-set scripts.

Mobile automation MCP service, providing Android/iOS device control capabilities for Cursor AI, supporting 39 operation tools, intelligent verification, test script generation, etc. It can be used without an AI key.

AutoMem MCP is an MCP client tool that provides persistent memory for AI assistants. By connecting to the AutoMem graph - vector memory service, MCP - compatible AI platforms such as Claude, Cursor, and GitHub Copilot can remember users' decisions, coding styles, and preferences across sessions and devices, achieving perfect memory and personalized interaction.

An MCP server for Aranet4 CO2 sensors, supporting device scanning, data collection and storage, historical query, and visualization functions, and providing AI - assisted configuration.

NodeMCU MCP is a service for managing NodeMCU devices, providing RESTful API, WebSocket interfaces, and MCP protocol integration, supporting remote monitoring, device control, and interaction with AI assistants.

The HomeyPro MCP server is a model context protocol service for interacting with the HomeyPro smart home system. It provides paginated access and comprehensive management functions for devices, zones, and processes, including features such as AI intelligent prompts and resource caching.

An MCP service for controlling mobile devices via AI, providing functions such as device management, application installation, and log acquisition, supporting Android and iOS platforms.

NetBrain MCP is an open-source network operation and maintenance platform that connects large language models with network devices through the Model Context Protocol, enabling AI-driven network configuration, diagnosis, and management. It also provides a professional Web terminal interface and network topology visualization functionality.