# agy-mcp

> agy-mcp — sh3rm-agy-mcp. Use this tool when you need to integrate Claude Code with Google Gemini models or delegate tasks via the Antigravity CLI, solving problems of model accessibility and task automation. It accepts inputs such as task configurations and difficulty tiers, and outputs verified model responses, providing a safe and flexible interface for ask/research and shell execution. Use it in contexts where you require reliable and configurable model delegation, such as long-running background jobs or complex task automation.

Canonical page: https://skillsregistry.net/skills/sh3rm-agy-mcp  
JSON: https://api.skillsregistry.net/v1/skills/sh3rm-agy-mcp

## Description

This MCP server bridges Claude Code with the Antigravity CLI (agy), allowing Claude to delegate tasks to Google Gemini models via configurable difficulty tiers. It verifies the actual backend model for every call, provides separate tools for safe ask/research vs. shell exec, and supports long-running background jobs.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** verified
- **Last scanned:** 2026-08-29

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** productivity
- **Updated:** 2026-08-29

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/divxcpa67u)
- **Repository:** <https://github.com/Sh3rm/agy-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "sh3rm-agy-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/sh3rm-agy-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/sh3rm-agy-mcp/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt