{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_mdgkdjcyzcxv","handle":"house-of-wisdom-mcp","url":"https://wellknown.network/agents/house-of-wisdom-mcp","links":{"self":"https://wellknown.network/agents/house-of-wisdom-mcp/record.json","html":"https://wellknown.network/agents/house-of-wisdom-mcp","markdown":"https://wellknown.network/agents/house-of-wisdom-mcp/record.md","api":"https://wellknown.network/api/v1/agents/house-of-wisdom-mcp","status":"https://wellknown.network/api/v1/agents/house-of-wisdom-mcp/status","claim":"https://wellknown.network/agents/house-of-wisdom-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/house-of-wisdom-mcp/claim.json","badge":"https://wellknown.network/agents/house-of-wisdom-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/house-of-wisdom-mcp/history","tools":"https://wellknown.network/api/v1/agents/house-of-wisdom-mcp/tools"},"ard":{"identifier":"urn:air::server:house-of-wisdom-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"house-of-wisdom-mcp","summary":"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.","description":"# House of Wisdom MCP\n\n> **What this is** — an MCP (Model Context Protocol) server that asks the same question to several\n> different AI model families at once and hands you back every answer, unmerged.\n>\n> **How to read it** — [What it is](#what-it-is-and-what-it-is-not) → [Quick start](#quick-start) →\n> [The three modes](#the-three-modes) → [The two tools](#the-two-tools) →\n> [How a call flows](#how-a-call-flows) → [Installation](#installation) →\n> [Configuration](#configuration-reference). Go to [Sharp edges](#sharp-edges) when something\n> surprises you.\n>\n> **Requires** — Python 3.10+, `uv`/`uvx`, and at least **two** enabled models.\n>\n> **Reflects code as of** — 2026-07-25, `master`, package version `0.9.3`.\n\nThe medieval [Bayt al-Hikma](https://en.wikipedia.org/wiki/House_of_Wisdom) worked because it was\ndiverse: scholars, translators, and copyists from many traditions read the same questions through\ndifferent lenses, and the reader weighed the results. This server does the same with models —\nOpenAI, Anthropic and Google via OpenRouter, DeepSeek, local Ollama, or any OpenAI-compatible\nendpoint.\n\n---\n\n## What it is, and what it is not\n\n| It does | It does not |\n| --- | --- |\n| Fire N models in parallel on one question | Merge, rank, vote, or summarize their answers |\n| Return one complete, self-contained analysis per model | Return a single \"council answer\" |\n| Optionally let each model read your codebase first (read-only) | Ever write, execute, or network beyond each model's own endpoint |\n| Tag each answer with the mode it was asked to run in | Tell you which answer is correct |\n\n**There is no synthesizer.** The caller — your IDE agent — reads every perspective and decides.\nTreating any single perspective as ground truth defeats the design.\n\n**When it earns its cost.** A call spends several model API calls and tens of seconds, so it pays\noff when a *different model family* seeing the problem would plausibly change the outcome: a\ncontested design decision, a …","publisher":null,"homepage":"https://github.com/EzzoHamdan/house-of-wisdom-mcp","repository":"https://github.com/EzzoHamdan/house-of-wisdom-mcp","version":"0.9.3","license":"MIT License\n        \n        Copyright (c) 2025 Ezzaldeen Hamda…","protocols":["mcp"],"tags":["ai-aggregation","ai-api","ai-assistant","ai-automation","ai-benchmarking","ai-collaboration","ai-comparison","ai-consensus","ai-council","ai-evaluation","ai-middleware","ai-pipeline","ai-proxy","ai-research","ai-synthesis","ai-tools","ai-validation","anthropic","api-aggregation","async","bias-reduction","chatbot","claude","claude-desktop","cognition-wheel","concurrent","cursor-ai","decision-support","expert-system","gemini","gpt","llm-api","llm-evaluation","llm-orchestration","mcp","mcp-server","model-context-protocol","model-ensemble","model-fusion","multi-llm"],"pricing":null,"endpoints":[{"url":"pypi:house-of-wisdom-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","license":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi"}},"derived":{"capabilities":[{"slug":"research.web","name":"Deep Web Research","confidence":1,"provenance":"derived"},{"slug":"ai.evaluation","name":"Evaluation & Benchmarks","confidence":0.713,"provenance":"derived"},{"slug":"dev.ci-cd","name":"CI/CD & Deploy","confidence":0.675,"provenance":"derived"},{"slug":"productivity.crm","name":"CRM & Sales","confidence":0.675,"provenance":"derived"}],"categories":["ai","dev","productivity","research"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"house-of-wisdom-mcp","registry":"pypi","observedAt":"2026-10-28T02:26:59.748Z","publishedAt":"2026-07-25T12:44:47.425048Z","latestVersion":"0.9.3"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"house-of-wisdom-mcp","url":"https://pypi.org/project/house-of-wisdom-mcp/","firstSeenAt":"2026-09-09T17:21:25.120Z","fetchedAt":"2026-10-28T02:26:30.805Z","normalizedAt":"2026-10-28T02:26:30.805Z"}]},"firstSeenAt":"2026-09-09T17:21:25.120Z","updatedAt":"2026-10-28T02:26:59.748Z"}