
AndroidTVMCP
A Model Context Protocol server that enables AI assistants to control Android TV devices, providing remote control functionality like navigation, playback control, app management, and device status monitoring.
README
AndroidTVMCP - Android TV Remote Control to MCP Bridge
A Model Context Protocol (MCP) server that provides Android TV remote control functionality to AI assistants and other MCP clients.
Overview
AndroidTVMCP bridges Android TV remote control capabilities with the Model Context Protocol, enabling seamless integration of Android TV control into AI-powered workflows and automation systems.
Features
- Device Discovery: Automatic detection of Android TV devices on the local network
- Remote Control: Full navigation and playback control capabilities
- App Management: Launch and switch between Android TV applications
- State Monitoring: Query device status and current state
- MCP Integration: Standard MCP protocol compliance for easy integration
Quick Start
Installation
Using Virtual Environment (Recommended)
# Create a virtual environment
python -m venv androidtvmcp-env
# Activate the virtual environment
# On Linux/macOS:
source androidtvmcp-env/bin/activate
# On Windows:
# androidtvmcp-env\Scripts\activate
# Install the package
pip install androidtvmcp
Global Installation
pip install androidtvmcp
Basic Usage
- Start the MCP server:
androidtvmcp --host localhost --port 8080
-
Configure your MCP client to connect to the server
-
Use Android TV control tools through your AI assistant
Example Commands
- Navigate: "Move up on the Android TV"
- Playback: "Pause the current video"
- Apps: "Launch Netflix on Android TV"
- Status: "What's currently playing on Android TV?"
Configuration
Create a configuration file config.json
:
{
"devices": {
"discovery": {
"enabled": true,
"timeout": 10
},
"connection": {
"timeout": 5,
"retry_attempts": 3
}
},
"mcp": {
"host": "localhost",
"port": 8080,
"transport": "stdio"
},
"logging": {
"level": "INFO",
"file": "androidtvmcp.log"
}
}
MCP Tools
Navigation Tools
atv_navigate
: Navigate Android TV interface (up, down, left, right, select, menu, back, home)atv_input_text
: Send text input to Android TV
Playback Tools
atv_playback
: Control media playback (play, pause, stop, fast_forward, rewind)atv_volume
: Adjust volume (up, down, mute)
App Management Tools
atv_launch_app
: Launch specific applicationsatv_get_apps
: List available applicationsatv_switch_app
: Switch between running applications
Device Tools
atv_get_devices
: List discovered Android TV devicesatv_get_status
: Get current device status and stateatv_power
: Power control (on, off, sleep)
MCP Resources
Device Information
device://[device_id]/info
: Device capabilities and informationdevice://[device_id]/status
: Current device statusdevice://[device_id]/apps
: Available applications
Current State
state://current_app
: Currently active applicationstate://playback
: Current playback statusstate://volume
: Current volume level
Development
Setup Development Environment
Using Virtual Environment (Recommended)
# Clone the repository
git clone https://github.com/pigeek/androidtvmcp.git
cd androidtvmcp
# Create and activate virtual environment
python -m venv venv
# Activate the virtual environment
# On Linux/macOS:
source venv/bin/activate
# On Windows:
# venv\Scripts\activate
# Install in development mode with dev dependencies
pip install -e ".[dev]"
Alternative Setup
git clone https://github.com/pigeek/androidtvmcp.git
cd androidtvmcp
pip install -e ".[dev]"
Run Tests
pytest
Development Tools
The devtools/
directory contains standalone scripts for manual testing and validation:
cd devtools
python test_command_processor.py # Test command processor functionality
python test_mcp_client.py # Test MCP client-server communication
python test_mcp_integration.py # Test MCP server integration
See devtools/README.md
for detailed information about each script.
Code Formatting
black src/ tests/
isort src/ tests/
Type Checking
mypy src/
Architecture
┌─────────────────┐ ┌─────────────────┐ ┌─────────────────┐
│ MCP Client │◄──►│ AndroidTVMCP │◄──►│ Android TV │
│ (AI Assistant) │ │ Server │ │ Devices │
└─────────────────┘ └─────────────────┘ └─────────────────┘
Components
- MCP Server: Handles MCP protocol communication
- Device Manager: Manages Android TV device discovery and connections
- Command Processor: Translates MCP requests to Android TV commands
- Network Layer: Handles Android TV protocol communication
Requirements
- Python 3.8+
- Android TV devices on the same network
- Network connectivity for device discovery
Troubleshooting
Common Issues
-
Device Not Found
- Ensure Android TV is on the same network
- Check firewall settings
- Verify device discovery is enabled
-
Connection Failed
- Check network connectivity
- Verify Android TV remote control is enabled
- Try restarting the Android TV device
-
Commands Not Working
- Ensure device is powered on
- Check if device supports the command
- Verify connection status
Debug Mode
Enable debug logging:
androidtvmcp --log-level DEBUG
Contributing
- Fork the repository
- Create a feature branch
- Make your changes
- Add tests
- Run the test suite
- Submit a pull request
License
MIT License - see LICENSE file for details.
Support
Related Projects
- androidtvremote2 - Android TV remote control library
- Model Context Protocol - Protocol specification
推荐服务器

Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。