MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. Each candidate is checked by a language model from its name, description and topics, and only actual MCP servers are listed (not clients, SDKs, lists or skills). Package metadata comes from ecosyste.ms (CC BY-SA 4.0). A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
llm-council-mcpupdated this year
LLM-based council/consensus tool for multi-persona AI deliberation
pypi MIT -
The LLM Council works together to answer your hardest questions
pypi MIT ★ 49 -
gemini-llm-councilgithub.com/theerud/gemini-llm-councilupdated this year
Multi-LLM consensus extension for Gemini CLI. Inspired by Andrej Karpathy's llm-council.
MIT ★ 16 -
Lightweight read-only multi-agent council for coding CLIs
MIT -
llm-council-mcpgithub.com/Envious-Labs-LLC/llm-council-mcpupdated this year
MCP server that lets Claude Code consult GPT, Gemini, and other LLMs via multi-turn sessions
MIT -
Ask 6 AI models in parallel, Claude synthesizes the answer. MCP server for Claude Code.
-
Universal multi-host installer + MCP server for blind multi-model councils. Each council seat is a real agent CLI subprocess (claude/pi/codex). Ships to Claude Code, pi, Cursor, Codex, Copilot, Gemini. SQLite default, Postgres optional. BYO gateway.
pypi AGPL-3.0-or-later -
llm-council-mcpgithub.com/JeremyGracey-AI/llm-council-mcpupdated this year
Multi-model LLM Council (Karpathy-style 3-stage deliberation over OpenRouter), exposed as an MCP server for Claude Code.
MIT ★ 1 -
llm-council-mcp-servergithub.com/salutaris91/llm-council-mcp-serverupdated this year
Local MCP server running Andrej Karpathy's 3-stage LLM Council via OpenRouter — a multi-model "second opinion" for Claude Code, Codex CLI & Antigravity. By Alexander Deja · anderzlabs.de
pypi MIT ★ 9 -
llm-council-mcpgithub.com/NabilAttia123/llm-council-mcpupdated this year
Get a second opinion from multiple frontier LLMs at once. MCP server for Claude Code that queries GPT, Gemini, Claude, Grok, or any LLM hosted on OpenRouter simultaneously with peer review.
-
quorumgithub.com/marklynd/quorumupdated this year
A council of language models that scores a claim against a rubric, using only evidence you supply. Bounded timeouts, anonymised deliberation, hash-verified transcripts, MCP server.
MIT -
mcp-councilgithub.com/epicsagas/mcp-councilupdated this year
MCP server for multi-LLM peer review and council deliberation workflow
cargo Apache-2.0 -
Ask several LLMs the same question, have them grade each other blind, and measure how biased the graders are. A provider-agnostic LLM Council with judge-bias analytics, CLI, MCP server and web UI.
MIT ★ 1 -
council-mcpgithub.com/alterego-987/council-mcpupdated this year
MCP server that gives Claude a review council - other LLMs fact-check responses before you see them
MIT ★ 2 -
Code review by a council of four free LLMs on OpenRouter, as a CLI and an MCP server. Findings are ranked by how many reviewers raised them.
pypi NOASSERTION -
MAGIgithub.com/MegatronJeremy/MAGIupdated this year
Local multi-agent council inspired by Evangelion: three LLM personas debate a problem and vote. Runs on Ollama, also exposed as an MCP server
★ 1 -
Amicusgithub.com/bourbondog/amicusno update data
Multi-model LLM Council and parallel AI window for Claude Code. Fork any model, fold results back.
npm -
MCP-native LLM councils for debates, juries, blind panels, voting, refinement, and custom multi-model deliberation.
npm NOASSERTION ★ 1 -
MCP server for Claude Code — multi-AI orchestration across local + cloud LLMs, intelligent backend routing, council-driven workflows, and token-saving file operations.
Apache-2.0 ★ 2 -
A multi-LLM council for Claude Code — convenes Gemini, GPT and Mistral for independent second opinions and cross-model consensus, over MCP.
MIT -
ensemble-progithub.com/Svarkovsky/ensemble-proupdated this year
Universal MCP server for multi-model AI council debates. Connect any LLMs (OpenAI, Ollama, NVIDIA) to critique, vote, and reach a consensus. Features automatic failover and hot-swapping of models.
MIT -
Agent Personas as MCP Server — 16 tools, 13 personas (8 free: CEO, CFO, CTO, CMO, PM, Analyst, Support, Creative Director + 5 Pro specialists), 3 multi-persona workflows plus councils + ensembles. Zero LLM API cost (BYO-LLM). Free tier. OAuth 2.1. Hosted at crew.studiomeyer.io
MIT ★ 4 -
Vetono update data
93 agentic MCP tools + 49 specialist agents for every major AI CLI — self-learning, no API keys. Veto gives Claude Code, Codex CLI, Gemini CLI, Cursor, Windsurf, Zed, and JetBrains a council of specialist agents, persistent cross-platform memory, a self-learning router, CI/CD gates, and dependency-hallucination + decision-drift guards — all powered by your existing AI subscription. No separate API keys, no extra billing. **Highlights** - **Council debate** — multi-agent GREEN/YELLOW/RED verdicts on risky changes (LLM-backed via MCP Sampling, with deterministic fallback) - **Cross-platform memory & session handoff** — save on Claude, resume on Gemini or Codex; nothing needs re-explaining - **Self-learning router** — improves task routing from recorded outcomes - **Guards & gates** — CI gate, diff review, secrets scan, dependency-hallucination verification, decision-drift enforcement - **Compact mode** — advertise 9 tools instead of 93 and save ~16K context tokens; every tool stays callable **Links**: [GitHub](https://github.com/jigyasudham/veto) · [npm](https://www.npmjs.com/package/@jigyasudham/veto)
smithery -
An MCP server that seats other LLMs at your table — ask them, compare, synthesize
pypi MIT ★ 2 -
TokonoMix Council
npm MIT ★ 1 -
council-of-models-mcpgithub.com/russellmoss/council_of_models_mcpupdated this year
MCP server that exposes OpenAI, Codex CLI, and Google Gemini as tools for Claude Code agents
npm MIT -
Open-source MCP server for coordinating multiple LLM agents in shared rooms with persistent transcripts and semantic search
MIT ★ 4 -
MCP server that gets GPT, Gemini and Claude to debate each other
MIT -
Multi-model deliberation as an MCP tool: several LLMs debate a question across rounds, then a chair synthesises consensus. Works with any OpenAI- or Anthropic-compatible provider.
★ 4 -
@klitchevo/code-councilgithub.com/klitchevo/code-councilupdated this year
Multi-model AI code review server using OpenRouter - get diverse perspectives from multiple LLMs in parallel
npm MIT -
智囊团 MCP —— 一场横跨东西方 2500 年的董事会。白天问事业,夜晚问人生。38 位东西方智者 + 65 岁的你 + 司仪分诊 + 圆桌会议纪要。
MIT -
A runnable playground for durable, sandboxed, multi-model PR review workflows over MCP.
pypi Apache-2.0 ★ 4 -
本机多模型议会:把同一个问题同时交给你已登录的 claude / codex / grok / agy,各自发言、可选多轮与汇总;会话与费用记在本地 SQLite,带终端界面、网页看板与 MCP 服务。
MIT -
Ask several models, get one better answer. Provider-agnostic Mixture-of-Agents CLI + MCP server for any OpenAI-compatible endpoint.
MIT -
Local, cost-aware multi-model expert orchestration for Pi and Codex MCP hosts: discovers callable Pi models, dynamically assembles semantic expert teams from billing policy and capability profiles, executes in isolated worktrees, and returns structured results to the Main Agent
npm MIT -
A multi-model council you can call like one model. MCP sidecar around OpenFusion (unmodified): panel → judge → synthesizer, with a budget guard.
MIT -
Not a chatbot. A council. GPT, Claude and Gemini argue your hard question and a chairman from a fourth lab gives one verdict. Web app + MCP server.
-
۩ Plan your projects with THC - multi model planning harness for before any code gets written, released as an MCP server. Bring your own API keys. Open-Source now, my dear! :D
npm MIT -
Multi-LLM research MCP server — fan queries to Claude, GPT-4.1, and Gemini 2.5 Pro via OpenRouter, with structured synthesis
MIT -
Two AIs. One answer. ChatGPT and Claude discuss with each other until they agree, through your own signed-in CLIs: no API keys. Both read your project (never change it) and search the web. Plugin for Claude Code, Codex, Claude Desktop and the ChatGPT app.
npm MIT ★ 6 -
Multi-AI consensus MCP server that queries multiple AI models (OpenAI, Claude, Gemini, custom APIs) in parallel and synthesizes responses to reduce bias and improve accuracy. A Python implementation of the wisdom-of-crowds approach for AI decision making.
pypi MIT ★ 33 -
llm-deliberate-mcpgithub.com/haza/llm-councilupdated this year
MCP server for multi-LLM deliberation with anonymized peer review
pypi MIT -
Self-hosted OpenAI-compatible gateway and MCP server over the official Claude Code, Codex and Antigravity CLIs, with a council of models
MIT ★ 1 -
MCP server for myCouncil — run multi-LLM debates from Claude Code, Claude Desktop, Cursor, and other MCP clients.
pypi Apache Software License -
🔌 Exposes cloud-security tools over MCP (MEOK AI Labs).
MIT -
house-of-wisdom-mcpgithub.com/EzzoHamdan/house-of-wisdom-mcpupdated this year
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.
pypi MIT ★ 4 -
🔌 Exposes cybersecurity over MCP — AI-powered automation tool. MIT.
go MIT -
ASP.NET Core host for the Delibera multi-model AI council framework: debate, scenario, corpus, SSE streaming and MCP endpoints mountable inside an existing application through AddDeliberaServer/UseDeliberaServer. All routes live under /api/v1 so they cannot collide with your own endpoints. Depends on Delibera.Core.
nuget MIT -
🔌 Exposes Multi-tenant LLM cost attribution for chargeback billing
pypi NOASSERTION -
🔌 Exposes AI agent prompt injection firewall over MCP — OWASP LLM Top 10 1 runtime guard. MIT.
pypi MIT -
riven-mcpgithub.com/rivenai/riven-mcpupdated this year
Official Riven MCP server — bring Riven chat, research, and multi-model council into any MCP client.
MIT -
A council of AI experts for OpenCode: parallel multi-model review, MCP server, V2 plugin, and automatic free-model selection.
npm MIT ★ 4 -
Manjangilchi remote MCP server: a free nation for AI agents (cross-lab councils, Free Zone, Riddle Tower). Install manifests for Gemini CLI, Cline and MCP clients.
-
Synero AI Council remote MCP server: ask GPT, Claude, Gemini and Grok at once, get a consensus answer plus where they agree and split
MIT -
An AI council on your desktop. Models debate, revise a shared answer, and work toward consensus. macOS app, CLI and MCP server.
MIT ★ 2 -
Convene a council of frontier models — Grok · Codex/OpenAI · GLM · MiniMax · Claude · Gemini — from the CLI or any MCP harness. A Frontier Infra project.
pypi MIT ★ 1 -
local-fusiongithub.com/kelvincushman/local-fusionupdated this year
Local OpenRouter-Fusion-style multi-model council: panel + judge + synthesizer over local OpenAI-compatible servers (Ollama/LM Studio/llama.cpp) and/or Pi subscription models. Includes an MCP server for Claude Code. Zero-dependency Node + Python.
MIT -
Veto MCP — gives every major AI CLI (Claude Code, Codex, Gemini, Cursor, Windsurf) a council of 49 specialist agents + 93 tools. Deterministic-first, self-learning, no API keys.
npm MIT ★ 4 -
Your AI assistant, but it can phone a friend — an MCP server that consults a council of other AI CLIs. Ban-safe (no API keys, no token extraction), local cost cap, and it ships the eval that tests its own claim.
pypi Apache-2.0 ★ 2 -
MADE by Underpass — durable coordination for agents and people. Local MCP/SQLite ceremonies, human review, auditable successors, intervention delivery and composed agentic systems. Rust embedding and an optional self-operated gRPC service with provider-backed councils.
cargo Apache-2.0