Antigravity Mobile Command MCP Server
Enables mobile control of Antigravity coding agents via Telegram, allowing task submission, plan approval, and artifact viewing.
README
🚀 Antigravity Mobile Command
Transform your mobile device into a remote Mission Control for your coding environment.
Antigravity Mobile Command is an "Agentic Bridge" that leverages Google Antigravity's native Model Context Protocol (MCP) and Artifact system to provide a bi-directional, real-time feedback loop via Telegram.

✨ Features
- 📱 Prompt-to-Action Loop: Send coding tasks from your phone, approve plans with inline buttons
- 📸 Visual Verification: Auto-receive screenshots and recordings of UI changes
- ✅ Interactive Governance: Approve or reject code diffs via Telegram buttons
- 🚨 Error Awareness: Get notified of terminal crashes with full stack traces
- 📊 Live Status Ticker: Real-time progress updates without message spam
🛠️ Quick Start
Prerequisites
- Python 3.10+
- A Telegram Bot Token (from @BotFather)
- Your Telegram Chat ID (from @userinfobot)
Installation
# Clone the repository
git clone https://github.com/yourusername/antigravity-telegram.git
cd antigravity-telegram
# Install dependencies
pip install -e .
# Or with uv
uv pip install -e .
Configuration
- Copy the example environment file:
cp .env.example .env
- Edit
.envwith your credentials:
TELEGRAM_BOT_TOKEN=your_bot_token_from_botfather
AUTHORIZED_CHAT_IDS=your_chat_id
ARTIFACTS_PATH=~/.gemini/antigravity/artifacts
Running
Run both Telegram bot and MCP server:
python -m src.main
Run only the Telegram bot:
python -m src.main --mode bot
Run only the MCP server (for Antigravity integration):
python -m src.main --mode mcp
🔌 Antigravity MCP Integration
1. Add to MCP Config
Add the Telegram bridge to your Antigravity MCP configuration (~/.gemini/mcp_config.json):
{
"mcpServers": {
"telegram-bridge": {
"command": "python",
"args": ["-m", "src.main", "--mode", "mcp"],
"cwd": "/path/to/antigravity-telegram",
"env": {
"TELEGRAM_BOT_TOKEN": "your_token",
"AUTHORIZED_CHAT_IDS": "your_chat_id",
"ARTIFACTS_PATH": "~/.gemini/antigravity/artifacts"
}
}
}
}
2. Copy the Workflow
Copy the workflow file to your Antigravity workflows:
cp workflows/mobile-command.md ~/.agent/workflows/
3. Use from Telegram
- Start a chat with your bot on Telegram
- Send
/startto verify the connection - Send
/prompt "Your coding task here" - Approve plans and review changes from your phone!
📱 Telegram Commands
| Command | Description |
|---|---|
/start |
Show welcome message and verify connection |
/prompt <text> |
Send a coding task to Antigravity |
/status |
Check current execution status |
/cancel |
Cancel the current operation |
/help |
Show help message |
🔧 MCP Tools Available
The following tools are exposed to Antigravity for communication:
| Tool | Description |
|---|---|
send_telegram_message |
Send messages to the user |
request_plan_approval |
Request approval for implementation plans |
request_change_approval |
Request approval for code changes |
send_artifact |
Send screenshots/recordings to Telegram |
update_status |
Update the status ticker message |
notify_error |
Send critical error notifications |
await_user_response |
Wait for user input |
🏗️ Architecture
┌─────────────────┐ ┌──────────────────┐ ┌─────────────────┐
│ 📱 Telegram │◄───►│ 🌉 Python │◄───►│ 🌌 Antigravity │
│ App │ │ Bridge │ │ Agent │
└─────────────────┘ └──────────────────┘ └─────────────────┘
│
▼
┌──────────────────┐
│ 📁 Artifact │
│ Watcher │
└──────────────────┘
📁 Project Structure
antigravity-telegram/
├── src/
│ ├── main.py # Entry point
│ ├── config.py # Configuration management
│ ├── bot/
│ │ ├── handlers.py # Telegram command handlers
│ │ ├── keyboards.py # Inline keyboard builders
│ │ └── message_queue.py # Async message queue
│ ├── mcp_server/
│ │ ├── server.py # MCP server implementation
│ │ ├── tools.py # MCP tool definitions
│ │ └── state.py # Approval state management
│ ├── monitors/
│ │ ├── artifacts.py # Artifact directory watcher
│ │ └── terminal.py # Terminal output monitor
│ └── utils/
│ └── formatting.py # Message formatting
├── config/
│ └── mcp_config.json # MCP config template
├── workflows/
│ └── mobile-command.md # Antigravity workflow
├── .env.example
├── pyproject.toml
└── README.md
🔒 Security
- Only authorized chat IDs can interact with the bot
- Bot tokens are stored in environment variables
- Session files are gitignored
📝 License
MIT License - see LICENSE for details.
🤝 Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
Built with ❤️ for the Antigravity community
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。