Agent Antigravity MCP Server

Model Context Protocol (MCP) server for Google Gemini Antigravity Agent.

Features

• Autonomous Code Execution: Run shell, Python, Node.js commands in remote Linux sandbox.

• Web Browsing & Search: Integrated google_search and url_context.

• Multimodal Inputs: Process text instructions and base64 images.

• Custom Functions: Support turn-based custom function calling.

• Remote MCP Servers: Connect external MCP servers to Antigravity agent.

• Model Selection: Choose between gemini-3.6-flash, gemini-3.5-flash-lite, and other Gemini models.

• Background Execution: Async interactions with background=True polling and max_total_tokens budget cap.

• Environment Config: Build remote sandbox config with file sources (inline/git/gcs) and network allowlist.

• Cron Triggers: Create, list, pause/resume, delete, run, and audit scheduled recurring interactions.

• GitHub PR Workflow: Point at a repo (public/private) + base branch; agent branches, does the task, pushes, opens the PR. Token injected via sandbox network allowlist, never in the prompt.

• Managed Agents: Register reusable named agents (system_instruction, default tools, base_environment) and invoke them by ID.

• Environments API: List/inspect/delete sandbox environments directly, and download a sandbox's full filesystem as a .tar.

• Hooks Config: Build hooks.json (pre/post code_execution/file-op interception, allow/deny) to mount into the sandbox via environment sources.

Related MCP server: gpal

Tools

Note: the Interactions API supports stream=true for real-time step deltas via the google-genai SDK directly (AntigravityClient.create_interaction(..., stream=True)), but it's not exposed as an MCP tool — MCP tool calls are synchronous request/response, so there's no way to surface incremental deltas over this transport.

Installation

As a Claude Code plugin (recommended)

This repo is a Claude Code plugin (.claude-plugin/plugin.json + .mcp.json + skills/agent-antigravity/). Add it as a local plugin marketplace and install:

/plugin marketplace add /path/to/agent-antigravity
/plugin install agent-antigravity

Set GEMINI_API_KEY (and GITHUB_TOKEN if using create_github_pr_task) in your shell environment before launching Claude Code — the plugin's .mcp.json passes them through. Installing the plugin registers the MCP server (via uv run, no manual venv needed) and the agent-antigravity skill together.

Standalone

uv venv --clear venv
uv pip install -e .

Configuration

Create .env file:

GEMINI_API_KEY=your_gemini_api_key
GITHUB_TOKEN=your_github_pat_with_repo_scope

GITHUB_TOKEN fallback used by create_github_pr_task when no github_token param given. Needs repo scope for private repos.

Optional:

AGENT_ANTIGRAVITY_LOG_LEVEL=INFO
AGENT_ANTIGRAVITY_SESSIONS_DB=/custom/path/sessions.db

Usage

Standalone, run server via stdio:

venv/bin/agent-antigravity

As a plugin, the MCP server auto-starts on enable and the agent-antigravity skill (skills/agent-antigravity/SKILL.md) auto-activates when a task matches — no manual venv/bin/... invocation needed.

Reliability

• Every API call tries the google-genai SDK first, falls back to direct REST on failure (logged at WARNING). REST calls retry on 429/5xx/transport errors with exponential backoff (3 attempts).

• Interaction session cache is SQLite-backed (~/.agent-antigravity/sessions.db by default) and survives process restarts.

• CI (.github/workflows/test.yml) runs the test suite on every push/PR.

Testing

uv pip install -e ".[dev]"
pytest -q

Credit

Structure and tool/resource/prompt patterns inspired by jules-mcp-server, an MCP server for Google Jules.

License

MIT — see LICENSE.