This server runs your prompt through three AI models in parallel via the Polza.ai API and returns their responses to Claude for synthesis. You get two presets: "china" (Moonshot Kimi, Qwen, DeepSeek) or "usa" (Gemini, Grok, OpenAI). It exposes four tools: tri_model_scan for basic consensus checks, tri_model_compare for evaluating options, tri_model_red_team for attacking ideas, and council_model_guide for understanding model strengths. Reach for this when a decision is ambiguous or you want multiple perspectives before committing, not for straightforward lookups or tasks a single model handles fine. Requires a Polza.ai API key and uses uvx for zero-config installation.
claude mcp add --transport stdio ivanantigravity-lgtm-model-council-mcp-server uvx model-council-mcp-server