An MCP server set that lets an AI assistant send prompts to second-model reviewers such as Codex, Gemini, Ollama, or Antigravity, either individually or through a unified orchestrator. It is used for code review, debating plans, summarizing large contexts, and running multi-provider comparisons from MCP clients like Claude Code, Cursor, or Claude Desktop.
From the registry: Bridge Claude with Google's Antigravity CLI (agy) for code review and second opinions
Please install the `ask-antigravity` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install Node.js** — Node.js v20.0.0 or higher is required to run the MCP server via npx. (https://nodejs.org/)
- **Install and authenticate Antigravity CLI** — Install the Google Antigravity CLI (`agy`) and log in once. The Ask Antigravity MCP server depends on the `agy` CLI being available in PATH and authenticated. (https://antigravity.google)
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["-y","ask-antigravity-mcp"]
Note: This server uses STDIO transport. The README does not specify any MCP config environment variables for Ask Antigravity; it relies on the external `agy` CLI already being installed and logged in. It is described as experimental and one-shot.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.AI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.
Persistent codebase knowledge graph. Survives session restarts and context compaction.
A powerful toolkit for coding, providing semantic retrieval and editing capabilities.