# claude-agy-mcp

> claude-agy-mcp — pymodel-claude-agy-mcp. Use this tool when you need to offload heavy tasks from Claude Code, such as file analysis, deep search, and web lookups, to a dedicated server for efficient processing and delegation. It solves problems of computational resource overload and provides a scalable solution with features like model routing, session continuity, and quota-aware failover. The tool accepts tasks as input and returns processed results, making it ideal for use cases requiring reliable and efficient task delegation.

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

## Description

MCP server that lets Claude Code delegate heavy tasks (file analysis, deep search, web lookups, adversarial review, and general delegation) to the Antigravity CLI (agy), with model routing, session continuity, timeout controls, and quota-aware failover.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** verified
- **Last scanned:** 2026-08-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** productivity
- **Updated:** 2026-08-28

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/ivi11o7cxp)
- **Repository:** <https://github.com/PyModel/claude-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": "pymodel-claude-agy-mcp"
    }
  }
}
```

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