agyforclaude
MCP server enabling delegation of tasks to the Antigravity (Gemini) CLI from any AI client supporting MCP.
README
agyforclaude
Universal MCP server + Claude skill for delegating tasks to the Antigravity (Gemini) CLI.
agyforclaude installs an MCP server and a Claude skill into ~/.claude/, making it work with any AI client that supports Model Context Protocol — Claude Code, OpenCode, Cursor, Codex, and more.
Prerequisites
- Node.js >= 18
- Antigravity CLI (
agy) — install it first
Install
npm install -g agyforclaude@latest
The postinstall hook automatically:
- Checks if
agyis installed - Appends
agyforclaudeto~/.claude/mcp.json - Copies the
agyskill to~/.claude/skills/agy/SKILL.md
Then restart your AI agent to pick up the new MCP server.
Usage
Your AI agent now has an agy_delegation tool:
| Param | Type | Default | Description |
|---|---|---|---|
prompt |
string |
(required) | The task to delegate to Gemini |
tier |
flash / flash-lo / pro |
flash |
Model tier |
dir |
string[] |
[] |
Workspace directories to include |
yolo |
boolean |
false |
Auto-approve agy tool permissions |
sandbox |
boolean |
false |
Run agy in sandbox mode |
Example prompts
- "Use agy to scaffold a Next.js app with TypeScript and Tailwind"
- "Delegate to Gemini: generate unit tests for
src/utils.ts" - "Use agy (pro tier) to review this PR for security issues"
The skill
The installed ~/.claude/skills/agy/SKILL.md reminds your agent:
- When to delegate (user asks, bulk work, cheap work)
- Always verify agy's output
- Never auto-merge
CLI Commands
After install, you also get agyforclaude on your PATH:
agyforclaude setup # Re-run setup (e.g. after moving node_modules)
agyforclaude uninstall # Remove from ~/.claude/ (also runs on npm uninstall)
agyforclaude status # Check if everything is properly installed
How it works
- MCP Server (
dist/mcp-server.js): Receives tool calls via stdio, spawnsagy --printwith the user's prompt, returns stdout. - Skill (
~/.claude/skills/agy/SKILL.md): Tells the AI when and how to use theagy_delegationtool. - CLI (
bin/agyforclaude): Manages installation/uninstallation of the above.
Dependencies
@modelcontextprotocol/sdk— MCP server SDKagy(external) — The Antigravity CLI (must be installed separately)
License
MIT
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.