
Council AI
**One prompt, many frontier models, one synthesized answer.** Council AI fans your prompt across 25+ models from 9 labs (Claude, GPT, Gemini, Grok, DeepSeek, Qwen, Mistral, Kimi, GLM) in parallel, then a moderator model synthesizes a consensus answer with a numeric agreement score. **Tools:** `council_query` (parallel fan-out + consensus), `council_review` (verdict-first multi-model code review — SHIP/NO-SHIP, findings confirmed by 2+ models, attributed dissents — built for coding agents), `council_query_with_rag` (the council reads your personal document library first), plus library search/list and models/usage introspection. **Auth:** Bearer Personal Access Token (`csa_…`) — mint one at [council-ai.app/settings](https://council-ai.app/settings?tab=mcp) (Ultra plan). Docs: [council-ai.app/mcp](https://council-ai.app/mcp)
First seen 2 Oct 2026. Evidence as of 5 Oct 2026.
Tools
No tool list captured yet.
Change history
No changes since the first observation. The first snapshot is the baseline.
| Source | Listing | First seen | Last seen | Versions |
|---|---|---|---|---|
| Smithery | 3omarkeshk3/council-ai | 2 Oct 2026 | 5 Oct 2026 | 1 |