Agyforclaude
БесплатноНе проверенMCP server enabling delegation of tasks to the Antigravity (Gemini) CLI from any AI client supporting MCP.
Описание
MCP server enabling delegation of tasks to the Antigravity (Gemini) CLI from any AI client supporting MCP.
README
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 - Configures the MCP server in
~/.claude/mcp.json(Claude Code) - Configures the MCP server in
~/.config/opencode/opencode.json(OpenCode) - Copies the
agyskill to~/.claude/skills/agy/SKILL.md
Then restart your AI agent to pick up the new MCP server.
Other agents (Cursor, Codex, Windsurf, etc.): MCP config is not automated. You'll need to manually add the server entry per your agent's docs. The server binary is at
dist/mcp-server.jsinside the agyforclaude package — find it withnpm root -g.
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 |
timeout |
number |
300 |
Max seconds for agy to complete (30-600). Default matches agy's built-in timeout. Increase for very large tasks. |
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
agyforclaude -p "prompt" [options] # Delegate a task directly from the command line
Options for Prompt Delegation:
-p,--prompt <string>: The task prompt to send to Gemini (required)-t,--tier <tier>: Model tier:flash(default),flash-lo,pro-d,--dir <dir>: Additional workspace directory to include (can be repeated)-y,--yolo: Auto-approve tool permissions (dangerous)-s,--sandbox: Run agy in sandbox mode--timeout <seconds>: Max seconds to wait (default: 300)
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
Установка Agyforclaude
У этого сервера нет опубликованного пакета — он собирается из исходников. Открой репозиторий и следуй инструкции в README.
▸ github.com/theoreticalthread/agyforclaudeFAQ
Agyforclaude MCP бесплатный?
Да, Agyforclaude MCP бесплатный — установка в пару кликов через Unyly без оплаты.
Нужен ли API-ключ для Agyforclaude?
Нет, Agyforclaude работает без API-ключей и переменных окружения.
Agyforclaude — hosted или self-hosted?
Self-hosted: сервер запускается локально на твоей машине командой из раздела установки.
Как установить Agyforclaude в Claude Desktop, Claude Code или Cursor?
Открой Agyforclaude на unyly.org, выбери вкладку своего клиента (Claude Desktop, Claude Code, Cursor) и нажми Install — конфиг сгенерируется автоматически, без правки JSON.
Похожие MCP
Fetch
Web content fetching and conversion for efficient LLM usage.
AWS KB Retrieval
Retrieval from AWS Knowledge Base using Bedrock Agent Runtime.
автор: modelcontextprotocolSpring AI MCP Server
Provides auto-configuration for setting up an MCP server in Spring Boot applications.
llm-analysis-assistant
A very streamlined mcp client that supports calling and monitoring stdio/sse/streamableHttp, and can also view request responses through the /logs page. It also
автор: xuzexin-hzCompare Agyforclaude with
Не уверен что выбрать?
Найди свой стек за 60 секунд
Автор?
Embed-бейдж для README
Похожее
Все в категории ai
