antigravity-claude-mcp
Allows Claude Code to consult Google Antigravity (Gemini, Claude, or GPT-OSS models) for independent code reviews and second opinions on plans or diffs.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@antigravity-claude-mcp Ask Antigravity to review my changes in src/auth.ts for edge cases"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
antigravity-claude-mcp
Give Claude Code a second brain. Ask Google Antigravity — Gemini 3 Pro, Claude, or GPT-OSS — for an independent code review or second opinion, right from inside Claude Code. One command. Zero dependencies.
claude mcp add antigravity -- npx -y antigravity-claude-mcpThat's it. Restart Claude Code, and Claude can now call ask_antigravity to get a second model's take on any plan or diff.
Why
Claude reviewing its own code is Claude reviewing its own code. You don't catch your own blind spots by thinking harder — you catch them with a different mind.
This bridges Claude Code to Google Antigravity's CLI (agy), so Claude can hand a plan or a diff to a different model family (Gemini 3 Pro by default) and get an independent verdict — before you do. Two models check the work; you make the call.
It's the wiring behind a simple loop:
You ── prompt ──▶ Claude validates ──▶ asks Antigravity (Gemini) ──▶ they agree on ONE plan
│
you approve ◀── Antigravity reviews the diff ◀── Claude writes the codeSee examples/CLAUDE_ANTIGRAVITY_LOOP.md for the full working agreement you can drop into any project.
Related MCP server: multi-ai-collab
Quickstart (2 minutes)
1. Install the Antigravity CLI (if you don't have it) and sign in once:
curl -fsSL https://antigravity.google/cli/install.sh | bash
~/.local/bin/agy -p "ping" --print-timeout 5m # opens a Google login the first time2. Add the MCP server to Claude Code:
claude mcp add antigravity -- npx -y antigravity-claude-mcp3. Check it's healthy (optional):
npx antigravity-claude-mcp doctor4. Restart Claude Code, run /mcp to approve the tool, and ask:
"Use ask_antigravity to review my changes in
src/auth.tsfor edge cases."
How it works
┌────────────┐ MCP (stdio, ┌─────────────────────────┐ agy -p ┌──────────────────┐
│ Claude Code│ JSON-RPC 2.0) │ antigravity-claude-mcp │ --model … │ Antigravity CLI │
│ (Claude) │ ───────────────▶ │ ask_antigravity tool │ ───────────▶ │ Gemini 3 Pro / │
│ │ ◀─────────────── │ (this package) │ ◀─────────── │ Claude / GPT-OSS │
└────────────┘ tool result └─────────────────────────┘ stdout └──────────────────┘The package is a tiny stdio MCP server that shells out to agy -p (Antigravity's headless print mode), optionally adding files/folders as context with --add-dir, and returns the model's text back to Claude.
The ask_antigravity tool
Param | Type | Required | Description |
| string | ✅ | The question, proposed approach, or review request. |
| string[] | Absolute file/folder paths. Antigravity reads them in full as context. | |
| string | Override the model (see below). Default: |
Models
Whatever your Antigravity account exposes via agy models, for example:
Gemini 3.1 Pro (High)← default (strong, and a different family from Claude)Gemini 3.5 Flash (Low|Medium|High)(fast/cheap)Claude Sonnet 4.6 (Thinking),Claude Opus 4.6 (Thinking)GPT-OSS 120B (Medium)
Why default to Gemini, not Claude? The whole point is an independent reviewer. Using a Claude model to review Claude's work defeats the cross-check. Override per call with
modelif you want a specific one.
Configuration
Set as environment variables on the MCP server (e.g. via claude mcp add ... -e KEY=VAL):
Variable | Default | Purpose |
| auto-detected | Absolute path to the |
|
| Default model for every call. |
|
| Headless print timeout. |
Troubleshooting
agy runs but prints "passed to Electron/Chromium" warnings.
You have the Antigravity IDE installed, and plain agy on your PATH is a symlink into Antigravity.app — that's the editor, not the CLI. This package auto-detects and skips it, preferring the real CLI at ~/.local/bin/agy. If you call agy by hand, use the full path or set AGY_BIN.
"Authentication required."
Sign in once interactively: ~/.local/bin/agy -p "ping" --print-timeout 5m, open the printed Google link, approve, and paste the code back into that prompt.
Tool doesn't appear in Claude Code.
Restart Claude Code after claude mcp add, then run /mcp and approve ask_antigravity. claude mcp list should show antigravity ✔ Connected.
vs. a proxy
Some projects route Claude Code's own traffic through Antigravity via an Anthropic-compatible proxy (i.e. Claude Code is "powered by" Antigravity). This is the opposite and complementary: Claude Code stays Claude, and Antigravity becomes a tool Claude can consult — so you get two genuinely different models in one loop instead of swapping one out for the other.
Requirements
Claude Code CLI
Antigravity CLI (
agy), signed inNode.js ≥ 18
License
MIT © Arjun Thilak
Available Tools
1 toolask_antigravityA
Get an INDEPENDENT second opinion or code review from Google Antigravity (default model: Gemini 3.1 Pro High) — a different model family than Claude, so it is a real cross-check, not Claude reviewing Claude. Provide a prompt; optionally pass paths (absolute file or folder paths) and Antigravity will read the ENTIRE file/folder as context before answering. Use it to validate an approach before coding, get an alternative design, or review code for bugs / edge cases / style.
Inputs: prompt (required), model, paths.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 1 tool
With only one tool, there is no possibility of ambiguity or confusion with other tools. The tool's purpose is clearly distinct as a second-opinion service.
Since there is only one tool, naming consistency is not an issue. The name 'ask_antigravity' is clear and follows a sensible verb_noun pattern.
The single tool is appropriate for the narrow, focused purpose of obtaining a code review or second opinion from a different AI model. While the typical range is 3-15, the server's scope justifies a minimal surface.
The tool fully covers the server's stated purpose: it accepts a prompt and optional file paths, enabling thorough context-aware cross-checks. No obvious gaps in functionality exist for this specific use case.
Maintenance
Related MCP Connectors
Multi-brand AI code review for Claude: up to 12 reviewers and a judge, no install.
Share context and questions between Claude instances — VS Code, claude.ai web, and mobile.
Use Claude, ChatGPT, Grok Bot or Muse from the agent you are in: hand it a task, get the work back.
Your AI apps as one team: hand work to Codex or Claude Code on your Mac, with a shared logbook.
Related MCP Servers
- -licenseNot gradedqualityNot gradedmaintenanceGives Claude access to multiple AI models (Gemini, OpenAI, OpenRouter, Ollama) for enhanced development capabilities including extended reasoning, collaborative development, code review, and advanced debugging.-
- AlicenseNot gradedqualityDmaintenanceLets Claude Code query multiple AI models (Gemini, Grok, ChatGPT, DeepSeek) for diverse perspectives, code reviews, debates, and more.MIT
- AlicenseAqualityDmaintenanceAllows Claude Code to request an independent code review from Google Antigravity (Gemini, Claude, or GPT-OSS) via the Antigravity CLI, providing a second opinion on plans or diffs.1145 npm3MIT
- AlicenseNot gradedqualityBmaintenanceEnables Claude Code to delegate implementation tasks to Antigravity CLI and OpenCode, run them fully autonomously, and then review and gate the results.1MIT