Council AI

One prompt, many frontier models, one synthesized answer.

CommunityOnlineNo sign-inGlobalFreeRead-only

What it can do

  • Council Query: Send a prompt to 25+ frontier AI models across 9 labs (Anthropic, OpenAI, Google, xAI, DeepSeek, Qwen, Mistral, Moonshot, z.ai) in parallel. Returns each model's independent response pl
  • Council Query With Rag: Like council_query, but first retrieves the most relevant passages from the user's personal Council RAG library (uploaded PDFs, Word docs, contracts, research papers, codebases
  • Council Review: Multi-model code review. Sends a unified diff (or code snippet) to multiple frontier AI models from different labs in parallel, each acting as an independent reviewer with an explicit

What data it sees

Do you need an account

No: the server works without sign-in

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 (Ultra plan). Docs: council-ai.app/mcp

Server tool list (7)

Raw names from tools/list. Only developers need these.

council_querySend a prompt to 25+ frontier AI models across 9 labs (Anthropic, OpenAI, Google, xAI, DeepSeek, Qwen, Mistral, Moonshot, z.ai) in parallel. Returns each model's independent response plus a moderator-synthesized consensus answer with an agreement score. Use when a single-model answer might hallucinate or when verification across labs matters (research, contracts, architecture, legal, medical, code review). Call get_models first to pick specific model IDs, and get_usage to check remaining budget. Bills against the user's Council AI monthly budget.
council_query_with_ragLike council_query, but first retrieves the most relevant passages from the user's personal Council RAG library (uploaded PDFs, Word docs, contracts, research papers, codebases) and injects them into every model's prompt. Use when the question is about content the user has uploaded — contract review, research synthesis across a paper library, code review against an architecture doc, etc. Ultra-tier only.
council_reviewMulti-model code review. Sends a unified diff (or code snippet) to multiple frontier AI models from different labs in parallel, each acting as an independent reviewer with an explicit verdict + findings contract. Returns a verdict-first synthesis: overall SHIP/NO-SHIP, consensus score, confirmed findings (flagged by 2+ models), then dissents (single-model findings with reasoning), then each reviewer's verdict. Diffs are capped at 14,000 characters — split larger changes by file or hunk and call once per chunk. Bills against the user's Council AI monthly budget like any council query.
library_searchSemantic search over the user's Council RAG library (uploaded PDFs, Word docs, contracts, research papers, codebases). Returns top-K chunks with source filename and page number. No model call, no budget consumption. Use to find direct quotes, check what the library contains, or scope a follow-up council_query_with_rag call.
library_listList the documents in the user's Council RAG library. Returns id, filename, source type, ingestion status, chunk count, and upload date for each document. No retrieval, no budget consumption.
get_modelsList the AI models available to the current user. Returns ID, provider, tier, context window, and capability flags (web search, vision, streaming). Use the IDs returned here as the `models` array argument to council_query / council_query_with_rag.
get_usageReturn the user's current monthly cost-budget consumption (current spend, budget cap, percentage used, days until reset). Use to decide whether to warn the user before invoking another council_query, or to suggest using cheaper models. Per Council's rule: never show dollar amounts to the user in the response — use percentages.