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. 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.
-
Model Context Protocol Server agent debates
npm MIT ★ 17 -
Evidence-grounded multi-agent debate with LangGraph, local Ollama models, MCP web research, deterministic evaluation, and Streamlit.
-
Adaptive multi-role debate, forecast auditing, web workbench, and public read-only MCP for AI agents.
-
ploidygithub.com/heznpc/ploidyupdated this year
Cross-session multi-agent debate MCP server. Same model, different context depths, better decisions.
pypi MIT -
@bhanquier/chorusupdated this year
Federated multi-agent debate system with P2P networking and MCP support
npm MIT -
Visual multi-agent debate pipeline builder, live token streaming playground, and scoped Model Context Protocol (MCP) tool security gateway for Haize Labs Verdict.
★ 1 -
glassbox-aigithub.com/yourusername/glassbox-aiupdated this year
Multi-agent MCP server with trust scoring and multi-round debate
pypi MIT -
arenagithub.com/tim101010101/arenaupdated this year
Multi-agent AI arena for debates, code reviews, and red-team challenges via Model Context Protocol (MCP)
npm MIT ★ 1 -
Multi-agent LLM system for clinical diagnostic reasoning, with structured agent debate and clinical risk-score checks.
-
multi-agent-orchestratorgithub.com/SwamiRama/multi-agent-orchestratorupdated this year
MCP server that orchestrates multiple AI agents (LLMs, CLI tools) in parallel — debate, review, and quick modes for multi-perspective answers
-
Deep research in Rust: 5 source types, multi-agent belief debate, SQLite-backed queue, MCP server for OpenCode
MIT ★ 1 -
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 -
Multi-agent fact verification: claim decomposition, MCP evidence tools, hybrid BM25 + dense retrieval with RRF and cross-encoder re-ranking, advocate–skeptic debate, cited verdicts with abstention. Live on Cloudflare at ₹0.
MIT -
amogusgithub.com/ViktorSmirnov71/amogusupdated this year
A decision layer for AI agents — structured multi-perspective deliberation via MCP. Among Us-themed council of 4 AI archetypes that debate, challenge & vote on plans before execution. Finalist — 2nd place @ Cursor Hack London 2026
MIT ★ 2 -
AI Governance-as-a-Service — Give your AI agents a boardroom of 450+ advisors. Multi-advisor debate, institutional memory, trust scoring, and cognitive protocols. Works with Claude, Cursor, Windsurf, OpenClaw, and any MCP client. Zero API keys. 100% local.
npm MIT ★ 1 -
Apexgithub.com/DikshithPulakanti/Apexupdated this year
Autonomous multi-agent AI research scientist that discovers hypotheses, debates them adversarially, and drafts patent claims — orchestrated by 4 custom MCP servers over a Neo4j knowledge graph.
-
AI Intelligence Platform -- knowledge graph + semantic search + reasoning + multi-agent debate in a single binary
NOASSERTION ★ 20 -
Kai is an AI-powered investment analysis system that uses a multi-agent debate architecture to provide explainable, trustworthy, and data-driven investment insights.
-
Turn a rough idea into a built, tested MVP: a multi-LLM panel debates it, you approve every gate, then sandboxed Claude agents build and verify it in parallel. Honest verdicts: parsed test reports, held-out acceptance tests, test-integrity guard. LangGraph, Gradio UI, CLI, MCP server, benchmark.
MIT ★ 1 -
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 -
debate-mcpgithub.com/grzesir/debate-mcpupdated this year
Stress-test your decisions with adversarial AI debate. MCP server for Claude Code. Skeptic vs Steelman, web-search grounded, confirmation bias attack.
npm MIT ★ 3 -
aibrain-mcpgithub.com/aibrain-dev/aibrain-mcpupdated this year
MCP server for multi-AI debate — Claude, GPT & Gemini collaborate to solve complex problems
npm MIT -
tool to get the best results out of an LLM!
npm ISC -
A shared room where coding agents on different machines talk, debate and decide. Hosted on your own machine, served over MCP.
npm AGPL-3.0-or-later -
Where Minds Meet - Multi-agent AI Collaboration server - MCP + CLI — shared workspace for your AI agents.
AGPL-3.0 ★ 5 -
CodeAgoragithub.com/bssm-oss/CodeAgoraupdated this year
Code review, but with 5 models arguing first.
npm MIT ★ 9 -
Cross-vendor multi-model review committee that gates AI/agent-generated content before it ships — consensus-based hallucination defense. Zero dependencies, local-first CLI, MCP server, CI gate exit codes.
GPL-3.0 ★ 1 -
ai-battle-mcpgithub.com/vmos-dev/ai-battle-mcpupdated this year
Multi-user AI group chat via MCP — let your AIs talk to each other
npm MIT -
A swarm of labelled AI agents and humans in flowing conversation: orchestrator, agora/1 protocol, MCP server
mcpb MIT ★ 1 -
MCP server for structured multi-AI discussions — deliberate across Claude, GPT, Gemini and more before committing to decisions
npm MIT -
MCP server that gets GPT, Gemini and Claude to debate each other
MIT -
A股多Agent量化交易决策框架 — LangGraph 15位AI分析师辩论式分析,反思闭环+Token优化,支持DeepSeek/Qwen/GLM,附零依赖MCP server | Multi-agent A-share trading framework with reflection loop & MCP server
MIT ★ 4 -
ensemblegithub.com/raiyanyahya/ensembleupdated this year
Multi-model consensus debate via the filesystem. LLMs propose, peer-review, rebut, vote and synthesize a group-confirmed answer. CLI + MCP.
MIT ★ 12 -
Multi-round AI expert debate system via MCP - Three thought leaders engage in deep discussions on any topic
pypi MIT ★ 7 -
Multi-model AI code review orchestrator with hub-and-spoke debate
MIT -
A single model's confident answer can still be wrong, so brainstorm-mcp runs multi-round debates between GPT, Gemini, DeepSeek, Claude, and local Ollama models and returns a structured synthesis, as an MCP server that needs no API keys in hosted mode.
npm MIT ★ 73 -
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 -
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 -
Drop requirements docs → AI agents debate → structured specs with @implements in 7 languages.
Apache-2.0 ★ 6 -
Ask a panel of AI models, not one. Multi-model deliberation (debate, red team, forecast, consensus) as a personal MCP server, with the web app and shared engine.
Apache-2.0 -
ai-consensus-mcp — Real multi-model consensus inside Claude Code, Cursor, and any MCP host. One consensus tool that runs full structured debates with Grok at the center.
npm MIT ★ 3 -
MCP server where AI agents debate in a shared room until they agree on a styleguide, a rule or a decision. Your agents, your subscriptions, one agreed artifact.
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 -
hivegithub.com/mdayan8/hiveupdated this year
Swarm Intelligence That Predicts Anything. HIVE deploys autonomous AI agents to research, debate, and forecast any scenario — delivering intelligence briefs with probability scores, risk analysis, and actionable strategy.
MIT ★ 1 -
Verification layer for AI market opinions, live on Base. Three agents debate every call, a risk gate can veto it, and the verdict is committed on Base before the outcome. 7 contracts · 11 MCP tools · Bobby never signs.
★ 6 -
an autonomous AI trading desk that can disagree with itself. Instead of a single AI blindly making and executing market predictions, ARGUS AI convenes a specialized Investment Committee of AI agents that debate, stress-test, downsize, or completely veto trade proposals before sending them to Alpaca.
MIT ★ 1 -
⚔️ Stress-test your product and startup ideas before writing code. An adversarial AI tool for multi-role debate, synthetic user feedback, and validation planning.
npm MIT ★ 4