# Model Council

> Use this tool when you need to leverage multiple AI models for a single prompt, generating diverse outputs for synthesis and analysis. Model Council solves the problem of limited perspective by providing a unified interface to consult multiple models, including USA and China presets, and returns a comprehensive set of outputs. It accepts a prompt as input and returns multiple model outputs, requiring a Polza.ai key for API access.

Canonical page: https://skillsregistry.net/skills/ivanantigravity-lgtm-model-council  
JSON: https://api.skillsregistry.net/v1/skills/ivanantigravity-lgtm-model-council

## Description

Model Council is a multi-model MCP server that sends the same prompt to three AI models simultaneously and returns all outputs for Claude to synthesize. It supports a USA preset (Gemini, Grok, OpenAI) and a China preset (Moonshot Kimi, Qwen, DeepSeek). All model calls are routed through the Polza.ai API, requiring a Polza.ai key.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-04-29

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/ivanantigravity-lgtm-model-council)
- **Repository:** <https://github.com/ivanantigravity-lgtm/model-council-mcp-server>

## 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": "ivanantigravity-lgtm-model-council"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/ivanantigravity-lgtm-model-council` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/ivanantigravity-lgtm-model-council/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