House of Wisdom MCP — multi-model consultation council. Diverse AI model families investigate independently and return their own perspectives; the orchestrator weighs them. Inspired by the medieval Bayt al-Hikma.
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"house-of-wisdom-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# House of Wisdom MCP > **What this is** — an MCP (Model Context Protocol) server that asks the same question to several > different AI model families at once and hands you back every answer, unmerged. > > **How to read it** — [What it is](#what-it-is-and-what-it-is-not) → [Quick start](#quick-start) → > [The three modes](#the-three-modes) → [The two tools](#the-two-tools) → > [How a call flows](#how-a-call-flows) → [Installation](#installation) → > [Configuration](#configuration-reference). Go to [Sharp edges](#sharp-edges) when something > surprises you. > > **Requires** — Python 3.10+, `uv`/`uvx`, and at least **two** enabled models. > > **Reflects code as of** — 2026-07-25, `master`, package version `0.9.3`. The medieval [Bayt al-Hikma](https://en.wikipedia.org/wiki/House_of_Wisdom) worked because it was diverse: scholars, translators, and copyists from many traditions read the same questions through different lenses, and the reader weighed the results. This server does the same with models — OpenAI, Anthropic and Google via OpenRouter, DeepSeek, local Ollama, or any OpenAI-compatible endpoint. --- ## What it is, and what it is not | It does | It does not | | --- | --- | | Fire N models in parallel on one question | Merge, rank, vote, or summarize their answers | | Return one complete, self-contained analysis per model | Return a single "council answer" | | Optionally let each model read your codebase first (read-only) | Ever write, execute, or network beyond each model's own endpoint | | Tag each answer with the mode it was asked to run in | Tell you which answer is correct | **There is no synthesizer.** The caller — your IDE agent — reads every perspective and decides. Treating any single perspective as ground truth defeats the design. **When it earns its cost.** A call spends several model API calls and tens of seconds, so it pays off when a *different model family* seeing the problem would plausibly change the outcome: a contested design decision, a …
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.