Antigravity Mobile Command MCP Server
Enables mobile control of Antigravity coding agents via Telegram, allowing task submission, plan approval, and artifact viewing.
README
š 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
- š± Prompt-to-Action Loop: Send coding tasks from your phone, approve plans with inline buttons
- šø Visual Verification: Auto-receive screenshots and recordings of UI changes
- ā Interactive Governance: Approve or reject code diffs via Telegram buttons
- šØ Error Awareness: Get notified of terminal crashes with full stack traces
- š Live Status Ticker: Real-time progress updates without message spam
š ļø 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
š 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!
š± 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 |
š§ 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 |
šļø Architecture
āāāāāāāāāāāāāāāāāāā āāāāāāāāāāāāāāāāāāāā āāāāāāāāāāāāāāāāāāā
ā š± Telegram āāāāāāŗā š Python āāāāāāŗā š Antigravity ā
ā App ā ā Bridge ā ā Agent ā
āāāāāāāāāāāāāāāāāāā āāāāāāāāāāāāāāāāāāāā āāāāāāāāāāāāāāāāāāā
ā
ā¼
āāāāāāāāāāāāāāāāāāāā
ā š Artifact ā
ā Watcher ā
āāāāāāāāāāāāāāāāāāāā
š Project Structure
antigravity-telegram/
āāā src/
ā āāā main.py # Entry point
ā āāā config.py # Configuration management
ā āāā bot/
ā ā āāā handlers.py # Telegram command handlers
ā ā āāā keyboards.py # Inline keyboard builders
ā ā āāā message_queue.py # Async message queue
ā āāā mcp_server/
ā ā āāā server.py # MCP server implementation
ā ā āāā tools.py # MCP tool definitions
ā ā āāā state.py # Approval state management
ā āāā monitors/
ā ā āāā artifacts.py # Artifact directory watcher
ā ā āāā terminal.py # Terminal output monitor
ā āāā utils/
ā āāā formatting.py # Message formatting
āāā config/
ā āāā mcp_config.json # MCP config template
āāā workflows/
ā āāā mobile-command.md # Antigravity workflow
āāā .env.example
āāā pyproject.toml
āāā README.md
š Security
- Only authorized chat IDs can interact with the bot
- Bot tokens are stored in environment variables
- Session files are gitignored
š License
MIT License - see LICENSE for details.
š¤ Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
Built with ā¤ļø for the Antigravity community
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.