Antigravity MCP Bridge

Antigravity MCP Bridge

Bridges cloud-based AI orchestrators with local systems, enabling file management, terminal execution, and autonomous background tasks through the Model Context Protocol.

Category
访问服务器

README

<div align="center">

<!-- HEADER LOGOS --> <img src="https://www.gstatic.com/lamda/images/gemini_sparkle_v002_d4735304ff6292a690345.svg" width="60" alt="Gemini"/>     <img src="https://upload.wikimedia.org/wikipedia/commons/thumb/5/51/Google_Cloud_logo.svg/1280px-Google_Cloud_logo.svg.png" width="140" alt="Google Cloud"/>     <img src="https://upload.wikimedia.org/wikipedia/commons/thumb/c/c3/Python-logo-notext.svg/115px-Python-logo-notext.svg.png" width="50" alt="Python"/>

⚡ Gemini Antigravity Bridge

The Open-Source Bridge Connecting Google Gemini & Cloud AI to Your Local Machine via the Model Context Protocol

<!-- BADGES --> Model Context Protocol Gemini Spark Google Cloud Python ngrok MIT License CI/CD GitHub Stars

Verified Proof of Concept: A single Gemini Spark prompt — "Create a calculator with unit tests" — produced, ran, and committed working Python code to GitHub in under 3 seconds. Zero human copy-pasting.

Architecture • Tools API • Quickstart • Google Ecosystem • Developer Docs • Resources & Links • Benefits

</div>

🧩 What Is This Project?

Gemini Antigravity Bridge breaks the barrier between Cloud AI and your local machine. It runs a local Model Context Protocol (MCP) server that exposes your entire operating system — terminal, files, compilers, and Git — to any MCP-compatible AI orchestrator over a secure HTTPS tunnel.

Connect it to Google Gemini Spark and you get a fully autonomous AI Software Engineer that can plan, code, test, fix, and ship software directly on your disk.

🏗️ System Architecture

┌────────────────────────────────────────────────────────────────────┐
│                🌐  GOOGLE CLOUD ECOSYSTEM                          │
│                                                                    │
│  ┌─────────────────┐  ┌──────────────────┐  ┌─────────────────┐  │
│  │  Gemini Spark   │  │  Google Workspace │  │  Vertex AI /    │  │
│  │  (Orchestrator) │  │  Docs/Drive/Gmail │  │  Cloud Run      │  │
│  └────────┬────────┘  └──────────────────┘  └─────────────────┘  │
└───────────┼────────────────────────────────────────────────────────┘
            │  JSON-RPC 2.0 (Streamable HTTP / SSE)
            │  HTTPS via ngrok / Cloudflare Tunnel
┌───────────▼────────────────────────────────────────────────────────┐
│          ⚡  ANTIGRAVITY MCP BRIDGE  (Your Machine)                │
│                                                                    │
│   /mcp  (Streamable HTTP)    /sse  (Server-Sent Events)           │
│   CORS · Authentication · 7 Registered MCP Tools                  │
│                                                                    │
│  ┌──────────────┐  ┌──────────────┐  ┌──────────────────────────┐ │
│  │  File System │  │   Terminal   │  │  Antigravity Subagents   │ │
│  │  Read/Write  │  │  Shell/CMD   │  │  (Autonomous Tasks)      │ │
│  └──────────────┘  └──────────────┘  └──────────────────────────┘ │
│  ┌──────────────┐  ┌──────────────┐  ┌──────────────────────────┐ │
│  │   Python     │  │  Node.js/npm │  │   Git / Docker / CI      │ │
│  └──────────────┘  └──────────────┘  └──────────────────────────┘ │
└────────────────────────────────────────────────────────────────────┘

Transport Protocol

Endpoint Protocol Best For
/mcp Streamable HTTP (MCP 2.0) Google Gemini Spark, Vertex AI, all modern MCP clients
/sse Server-Sent Events (SSE) Legacy MCP clients, custom integrations
/messages HTTP POST Posting messages in SSE sessions

🧰 Complete Tools Reference

🔧 Tool 1: run_system_command

Execute any shell, PowerShell or Bash command. Captures exit code, stdout, stderr.

Param Type Required Description
command string ✅ Full shell command to execute
working_dir string ❌ Working directory path (defaults to CWD) 
// Example: Run Python unit tests
{
  "name": "run_system_command",
  "arguments": {
    "command": "python -m pytest tests/ -v",
    "working_dir": "C:/Users/dev/myproject"
  }
}

Use for: Running Python/Node/Java/Rust, pip install, npm install, git operations, test runners, Docker, CI pipelines.

📝 Tool 2: write_file

Create or overwrite any file on disk with AI-generated content. Auto-creates directories.

Param Type Required Description
file_path string ✅ Absolute or relative file path
content string ✅ Full content to write 
// Example: Write a FastAPI route
{
  "name": "write_file",
  "arguments": {
    "file_path": "src/api/routes.py",
    "content": "from fastapi import APIRouter\nrouter = APIRouter()\n\n@router.get('/health')\ndef health(): return {'status': 'ok'}"
  }
}

Use for: Writing source code, configs, Dockerfiles, GitHub Actions YAML, Markdown docs, .env files.

📖 Tool 3: read_file

Read and return the full content of any local file.

Param Type Required Description
file_path string ✅ Path to the file 
{
  "name": "read_file",
  "arguments": { "file_path": "src/main.py" }
}

Use for: Inspecting code before refactoring, reading logs, auditing configs, reading datasets.

📂 Tool 4: list_directory

Enumerate files and directories with type and size.

Param Type Required Description
directory_path string ❌ Directory to list (defaults to CWD) 
{
  "name": "list_directory",
  "arguments": { "directory_path": "C:/Users/dev/myproject" }
}

Use for: Discovering project structure, verifying files were created, auditing repos.

🤖 Tool 5: run_agent_task

Spawn an autonomous long-running Antigravity AI subagent for complex multi-step goals. Returns instantly with a task_id.

Param Type Required Description
prompt string ✅ High-level natural language objective
workspace_dir string ❌ Directory for the agent to operate in 
{
  "name": "run_agent_task",
  "arguments": {
    "prompt": "Refactor all Python files to use async/await. Run tests after each file.",
    "workspace_dir": "C:/Users/dev/myproject"
  }
}

Use for: Large-scale refactoring, full feature development, autonomous TDD, security audits.

📊 Tool 6: get_agent_status

Poll the live progress, output, and errors of a background subagent task.

Param Type Required Description
task_id string ✅ Task ID from run_agent_task 
{
  "name": "get_agent_status",
  "arguments": { "task_id": "a1b2c3d4" }
}
// Returns: { "status": "completed", "output": "...", "error": null }

📦 Tool 8: create_full_project (1-Click Composite)

Creates an entire project directory, writes all code files, and executes initial setup/test commands in a single tool call with 1 permission confirmation.

Param Type Required Description
project_name string ✅ Folder name of the new project
files object ✅ Dictionary of {"filename": "content"}
setup_commands array ❌ List of shell commands to run after creation

⚡ Tool 9: batch_write_files (Composite)

Writes or updates multiple files at once in a single dictionary mapping. Reduces permission prompts from N to 1.

Param Type Required Description
files object ✅ {"src/app.py": "...", "tests/test.py": "..."}
base_dir string ❌ Root directory for files

💻 Tool 10: run_batch_commands (Composite)

Executes a sequence of shell/PowerShell commands in order within a single tool call.

Param Type Required Description
commands array ✅ ["pip install -r requirements.txt", "pytest"]
working_dir string ❌ Target working directory
stop_on_error boolean ❌ Halts sequence if a command fails (default: true)

✏️ Tool 11: edit_file

Performs surgical search-and-replace on existing files without rewriting the entire file.

Param Type Required Description
file_path string ✅ Path to file to modify
find_text string ✅ Exact string to search for
replace_text string ✅ Replacement content

➕ Tool 12: append_file

Appends content to the end of a file (or creates it if missing).

Param Type Required Description
file_path string ✅ File path
content string ✅ Text to append

💬 Tool 13: list_antigravity_conversations

Lists all active Antigravity conversations and projects with real sidebar titles, message counts, task counts, and conversation IDs.

📨 Tool 14: inject_message

Injects instructions directly into any Antigravity conversation inbox, waking the Antigravity Language Server engine.

Param Type Required Description
conversation_id string ✅ Target Antigravity conversation UUID
message string ✅ Message content
title string ❌ Message title notification

🧠 Tool 15: get_bridge_history / save_session_note

Cross-client persistent memory shared between Gemini Spark and Antigravity.

🔗 Google Ecosystem Integration

<table> <tr> <td width="50%">

<img src="https://www.gstatic.com/lamda/images/gemini_sparkle_v002_d4735304ff6292a690345.svg" width="20"/> Gemini Spark

Connect your bridge to Gemini via Custom Connected Apps.

</td> <td width="50%">

<img src="https://upload.wikimedia.org/wikipedia/commons/thumb/5/51/Google_Cloud_logo.svg/100px-Google_Cloud_logo.svg.png" width="80"/> Google Cloud

Deploy the bridge to Cloud or integrate with Cloud AI.

</td> </tr> <tr> <td>

<img src="https://www.gstatic.com/images/branding/product/1x/vertex_ai_64dp.png" width="22"/> Vertex AI

Enterprise-grade AI orchestration with local execution.

</td> <td>

<img src="https://upload.wikimedia.org/wikipedia/commons/a/a5/Google_Calendar_icon_%282020%29.svg" width="22"/> Google Workspace

Use Docs, Drive, Gmail as AI context sources.

</td> </tr> </table>

📚 Official Documentation & External Resources

🔵 Model Context Protocol (MCP)

Resource Link
🏠 MCP Official Website modelcontextprotocol.io
📖 MCP Introduction modelcontextprotocol.io/introduction
📖 MCP Quickstart Guide modelcontextprotocol.io/quickstart
📖 MCP Specification spec.modelcontextprotocol.io
🐍 Python MCP SDK (Official) github.com/modelcontextprotocol/python-sdk
📦 MCP on PyPI pypi.org/project/mcp
🐙 MCP GitHub Organization github.com/modelcontextprotocol
📖 MCP Transports Reference modelcontextprotocol.io/docs/concepts/transports
📖 MCP Tools Reference modelcontextprotocol.io/docs/concepts/tools

🟣 Google Antigravity (AGY)

Resource Link
🏠 Antigravity Home antigravity.google
📖 Antigravity Docs antigravity.google/docs
📖 MCP Integration Guide antigravity.google/docs/mcp
📖 Skills System antigravity.google/docs/skills
📖 Python SDK antigravity.google/docs/sdk
📖 Hooks & Plugins antigravity.google/docs/hooks
📖 Agent Permissions antigravity.google/docs/permissions
📖 Changelog antigravity.google/changelog

🔵 Google Gemini & AI APIs

Resource Link
🏠 Google Gemini App gemini.google.com
📖 Gemini API Documentation ai.google.dev/gemini-api/docs
📖 Gemini API Quickstart ai.google.dev/gemini-api/docs/quickstart
📖 Gemini for Google Workspace workspace.google.com/intl/en/products/gemini
📖 Google AI Studio aistudio.google.com
📖 Connected Apps (MCP) Help support.google.com/gemini?p=lm_custom_mcp_trust
🐙 Google Generative AI GitHub github.com/google-gemini

☁️ Google Cloud Platform

Resource Link
🏠 Google Cloud Console console.cloud.google.com
📖 Vertex AI Documentation cloud.google.com/vertex-ai/docs
📖 Cloud Run Documentation cloud.google.com/run/docs
📖 Cloud Build Documentation cloud.google.com/build/docs
📖 Google Cloud APIs Explorer cloud.google.com/apis
📖 AI & Machine Learning Products cloud.google.com/products/ai

🐍 Python & Core Libraries

Resource Link
🏠 Python Official Website python.org
📖 Python Docs docs.python.org/3
📦 PyPI Package Index pypi.org
📖 pip Documentation pip.pypa.io/en/stable
📖 asyncio Documentation docs.python.org/3/library/asyncio.html
📖 subprocess Documentation docs.python.org/3/library/subprocess.html

🌐 Web & ASGI Framework

Resource Link
🏠 Uvicorn (ASGI Server) uvicorn.org
📖 Uvicorn Docs uvicorn.org/settings
🏠 Starlette Framework starlette.io
📖 Starlette Docs starlette.io/applications
📖 Starlette Routing starlette.io/routing
📖 CORS Middleware starlette.io/middleware/#corsmiddleware
🏠 FastAPI fastapi.tiangolo.com
📖 FastAPI Docs fastapi.tiangolo.com/tutorial

🔒 Tunneling & Secure Exposure

Resource Link
🏠 ngrok Official Website ngrok.com
📖 ngrok Documentation ngrok.com/docs
📖 ngrok HTTP Tunnels ngrok.com/docs/http
📦 pyngrok (Python SDK) pypi.org/project/pyngrok
📖 pyngrok Docs pyngrok.readthedocs.io
🏠 Cloudflare Tunnel cloudflare.com/products/tunnel
📖 Cloudflare Tunnel Docs developers.cloudflare.com/cloudflare-one/connections/connect-networks

📡 JSON-RPC & SSE Specifications

Resource Link
📖 JSON-RPC 2.0 Specification jsonrpc.org/specification
📖 Server-Sent Events (SSE) — MDN developer.mozilla.org/en-US/docs/Web/API/Server-sent_events
📖 HTTP Status Codes — MDN developer.mozilla.org/en-US/docs/Web/HTTP/Status

🔧 Development Tools

Resource Link
🏠 Git git-scm.com
📖 Git Documentation git-scm.com/doc
🏠 GitHub github.com
📖 GitHub CLI (gh) cli.github.com
🏠 Python IDLE docs.python.org/3/library/idle.html
📖 pytest Testing Framework docs.pytest.org
📖 unittest (Built-in) docs.python.org/3/library/unittest.html

🚀 Quickstart

Prerequisites

Python ngrok Git

Step 1 — Clone & Install

git clone https://github.com/nandhakumar-murugan/antigravity-mcp-bridge.git
cd antigravity-mcp-bridge
pip install -r requirements.txt

Step 2 — Add Your ngrok Token

Get your token at dashboard.ngrok.com/get-started/your-authtoken

Edit run_with_tunnel.py:

AUTHTOKEN = "your_ngrok_authtoken_here"

Step 3 — Launch

# Windows (Double-click or run):
start_server.bat

# macOS / Linux:
python run_with_tunnel.py

Output:

[INFO] NGROK MCP TUNNEL IS LIVE!
[LINK] PASTE THIS IN GEMINI SPARK: https://xxxx.ngrok-free.dev/mcp

Step 4 — Connect to Gemini Spark

  1. Open gemini.google.com
  2. Go to Settings → Custom Connected Apps
  3. Paste: https://xxxx.ngrok-free.dev/mcp
  4. Accept permissions → Click Save
  5. Type @Antigravity System Bridge in any chat to activate!

💻 Developer Integration Guide

Python (Official MCP SDK)

import asyncio
from mcp.client.session import ClientSession
from mcp.client.streamable_http import streamable_http_client

async def main():
    url = "https://xxxx.ngrok-free.dev/mcp"
    async with streamable_http_client(url) as (read, write):
        async with ClientSession(read, write) as session:
            await session.initialize()
            tools = await session.list_tools()
            print([t.name for t in tools.tools])

            # Run a command
            result = await session.call_tool("run_system_command", {
                "command": "python --version"
            })
            print(result.content[0].text)

asyncio.run(main())

cURL (Any Language)

curl -X POST https://xxxx.ngrok-free.dev/mcp \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"my-app","version":"1.0"}}}'

Claude Desktop Config

{
  "mcpServers": {
    "antigravity-bridge": {
      "command": "python",
      "args": ["run_with_tunnel.py"],
      "env": { "NGROK_AUTHTOKEN": "your_token" }
    }
  }
}

👥 Who Benefits

🎓 Students

  • See real code written and run on your disk — not in fake sandboxes
  • AI handles pip install, virtual environments, and PATH setup for you
  • Learn debugging by watching the AI fix real terminal errors live

💻 Engineers

  • Full autonomous TDD: AI writes code → runs tests → fixes failures → repeats
  • Delegate entire features: "Build a REST API with auth" → done in minutes
  • No more copy-pasting between chat and editor

🔬 Researchers

  • Run local Python pipelines without uploading sensitive data to the cloud
  • Automate experiment scripts, benchmarks, and data analysis conversationally
  • Use local GPU compute via terminal commands

📁 Project Structure

antigravity-mcp-bridge/
├── server.py               # Core MCP server with all 7 tool definitions
├── run_with_tunnel.py      # One-click launcher (server + ngrok tunnel)
├── start_server.bat        # Windows double-click starter
├── test_client.py          # MCP connection verification script
├── calculator.py           # Example: AI-generated code via Gemini Spark
├── test_calculator.py      # Example: AI-generated tests (all 6 passed)
├── requirements.txt        # Python dependencies
├── .gitignore
├── LICENSE                 # MIT
└── README.md

📦 requirements.txt

mcp>=2.0.0
uvicorn
fastapi
pyngrok
python-dotenv

🛡️ Security

  • All traffic is TLS-encrypted via ngrok HTTPS
  • ngrok Authtoken prevents unauthorized access
  • 180-second command timeout on all terminal executions
  • terminate_task immediately halts any running subagent
  • All operations are fully visible in your local terminal

📄 License

MIT License — see LICENSE for details.

<div align="center">

Built with the Google Ecosystem. Powered by Open Standards.

Gemini Cloud MCP Python ngrok GitHub

⭐ Star this repo if it helped you! | 🍴 Fork to customize for your team

🐛 Report Issues · 💬 Discussions · 🤝 Contribute

</div>

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选