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.
-
MCP Servers
npm MIT ★ 1 -
MCP-сервер, который организует работу нескольких LLM на основе паттерна Planner-Executor-Reviewer.
MIT -
multi-llm-mcpgithub.com/mai-yyy/multi-llm-mcpupdated this year
一个让 Claude Code 调用 Codex 干活,并可以同时调用多个模型(GPT、Kimi、DeepSeek 等)的 MCP 工具。
MIT ★ 118 -
A Model Control Protocol (MCP) server that allows cross-checking responses from multiple LLM providers simultaneously
MIT ★ 15 -
@llm-flow/multi-modelgithub.com/dandyrandy/llm-flowupdated this year
Run a prompt against multiple AI provider CLIs in parallel; ships as CLI and MCP server
npm MIT -
MCP server built on the official Python SDK that compares Claude, OpenAI and Gemini answers side by side, with a small provider-adapter layer.
MIT -
MCP server for multi-agent discussions — any AI agent (Claude/Codex/Gemini) as host, others as consultants. Uses CLI subscriptions, not API keys. 多 Agent 讨论 MCP Server:任意 AI Agent 做主控,其他做顾问,使用订阅账号无需 API Key。
MIT -
SequentialThinkinggithub.com/LseKit/SequentialThinkingupdated this year
Multi-step sequential thinking MCP server powered by large language models — structured reasoning with self-MoA and iterative thinking modes
pypi MIT ★ 1 -
LLM-COST-TRACKER-MCP-Server-NPM-Package-github.com/dominiquekossi/LLM-COST-TRACKER-MCP-Server-NPM-Package-updated this year
LLM Cost Tracker is a complete, production-ready NPM package that provides accurate token-based cost tracking for Large Language Models (LLMs). It includes a built-in MCP Server, a flexible budget manager, multi-provider support, usage analytics, cost simulation, and an extensible architecture for storage and pricing.
MIT -
FYP-XploitEye-Web-and-System-Vulnerabilities-using-Agents-LLMs-github.com/shoaib1522/FYP-XploitEye-Web-and-System-Vulnerabilities-using-Agents-LLMs-updated this year
XploitEye is a state-of-the-art, AI-powered multi-agent cybersecurity platform designed to automate the complete Cyber Kill Chain. By orchestrating advanced Large Language Models (LLMs) and industry-standard security tools, XploitEye provides a unified interface for both Red Team (Offensive) and Blue Team (Defensive) operations.
-
Wwise-MCP is a Model Context Protocol (MCP) server that enables large language models (LLMs) to interact with the Wwise Authoring application. It exposes a set of tools built on a custom Python WAAPI library, allowing MCP clients such as Claude or Cursor to automate and compose complex, multi-step Wwise workflows.
Apache-2.0 ★ 79 -
MCPSERVERgithub.com/adinath09/MCPSERVERupdated this year
This project demonstrates an intelligent AI agent built using LangGraph that can dynamically select and call multiple tools via the MCP (Multi-Call Protocol). The agent integrates asynchronous execution, external APIs, and large language models (Groq) to process user queries efficiently.
-
A lightweight, pure web search solution for large language models, supporting multi-engine aggregated search, deep reflection and result evaluation. A balanced approach between web search and deep research, providing a framework-free implementation and mcp server for easy developer integration.
Apache-2.0 ★ 2 -
Multi-agent LLM system for clinical diagnostic reasoning, with structured agent debate and clinical risk-score checks.
-
Multi-agent LLM research platform: parallel data agents, synthesis agents, deterministic guardrails, MCP server
MIT ★ 1 -
A production-style multi-agent system that generates context-aware briefs. Built on MCP + A2A, with persistent memory (Chroma), dynamic tool routing, self-critique, distributed tracing (Arize Phoenix), an LLM-as-judge eval harness, and Redis caching.
★ 1 -
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
-
Multi-account Google Workspace (Gmail, Drive) for LLM agents — 100% local, default-deny policy, human-in-the-loop access. A macOS MCP server.
MIT -
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 -
qiaomu-llm-mcpgithub.com/joeseesun/qiaomu-llm-mcpupdated this year
把多模型 Provider、本地密钥和 HeavySkill 讨论统一成 MCP 网关 | Local MCP gateway for multi-provider LLM routing, secrets, and HeavySkill discussions.
MIT ★ 49 -
Multi_Agent_Python_Code_Auditorgithub.com/spranavk-03/Multi_Agent_Python_Code_Auditorupdated this year
Multi-Agent AI Code Auditor is a Python-based code review system that uses AST parsing, Bandit, Radon, and LLM-based agents to analyze code for security, quality, and complexity. The findings are summarized into a final report, saved as JSON, and benchmarked across multiple Python programs.
★ 1 -
llm-arena-mcpgithub.com/snowbikemike/llm-arena-mcpupdated this year
Multi-LLM MCP Server — Route prompts to GPT-4o, Claude, Gemini, Grok, Llama, and Mistral simultaneously. Compare responses side-by-side with automated behavioral pattern detection.
npm MIT -
nous-roboticsgithub.com/Daniel-Visit/nous-roboticsupdated this year
LLM-Orchestrated Multi-Robot Coverage Planning via MCP + ROS2
MIT -
multi-agent-reviewergithub.com/Ishaan300104/multi-agent-reviewerupdated this year
LLM-based Multi Agent Research Paper Reviewer (arXiv) using custom Model Context Protocol (MCP) server.
★ 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 -
Self-hosted multi-agent AI orchestration demo: n8n, MCP server, LLM routing, self-updating knowledge base
MIT -
A Multi-Organization Azure DevOps Model Context Protocol (MCP) server with LLM-optimized context handling.
Apache-2.0 -
ai-orchestrator-officialgithub.com/namangoyal3/ai-orchestrator-officialupdated this year
Multi-model AI gateway for LLM routing, specialized agents, and MCP-compatible tool orchestration.
-
organismogithub.com/turbillon50/organismoupdated this year
Semantic caching layer for multi-agent LLM systems. Stop paying your LLM to recompute the same thing twice. MCP-native.
Apache-2.0 -
Multi-agent LLM red-teaming and eval lab: attacks a RAG chatbot with prompt injection, poisoned documents and PII probes, scores replies via an MCP server (Presidio, DeepEval), and logs every run to SQLite for prompt and model comparison.
-
geepers-mcpgithub.com/lukeslp/geepers-mcpupdated this year
Multi-agent orchestration and LLM provider abstraction via MCP protocol - 72 specialist agents, 22 orchestration patterns
pypi MIT -
geepers-agentsgithub.com/lukeslp/geepersupdated this year
Multi-agent orchestration platform: 72 agents, 53 skills, 6 MCP servers, LLM provider abstraction, and 30+ data-fetching tools
pypi MIT -
secondlookupdated this year
Multi-provider code review via MCP. Get a second look on your code from any LLM.
pypi MIT -
mcp-multi-editgithub.com/eaisdevelopment/mcp-multi-editupdated this year
Multi-Edit MCP Server for Agentic Coding. Enable multiple edits to a file in a single step. Saves time and tokens of LLM.
npm NOASSERTION -
MCP server over SEC EDGAR filings with hand-written single-agent and multi-agent (planner → parallel researchers → synthesizer) LLM researchers, a live SSE UI, and a blind evaluation of when multi-agent is worth it.
-
MCP-native LLM councils for debates, juries, blind panels, voting, refinement, and custom multi-model deliberation.
npm NOASSERTION ★ 1 -
Local, agent-agnostic context store for multi-agent LLM systems. Cold resume measured flat at 2,679 tokens regardless of board size.
★ 1 -
Benchmark LLMs on your own scenarios with a multi-judge panel. Full MCP server (tools, resources, prompts, progress) plus local GUI, CLI, and desktop app. One OpenRouter key.
MIT -
Agentic AI multi-agent application with local LLM (Ollama) and MCP server support. 45 agents, 50 workflows, fully offline. Jaspal 9891156880
★ 1 -
Cheap Money-Saving Self-hosted AI agent workspace with tool calling, MCP, multi-model routing, sandboxed execution, multi-agent workflows, and LLM-authored 3D character animation rendered with Three.js.
MIT ★ 195 -
Pure Rust AI coordination — MCP server, multi-provider inference routing, local-first LLM orchestration. Sovereign AI for distributed computing. AGPL-3.0
NOASSERTION -
Institutional-grade trading decision engine with memory, multi-LLM support, and advanced market structure analysis
npm MIT -
ADEPT: Agentic Discovery and Exploration Platform for Tools — A three-tier secure framework for multi-agent scientific workflows with 28+ MCP tools, 10 client interfaces, and declarative multi-LLM configuration.
NOASSERTION ★ 4 -
MCP server for the three.ws multi-provider LLM router: discover models and run chat completions through any of them.
Apache-2.0 ★ 9 -
Multi-agent RAG on LangGraph: agents research, write and fact-check cited daily notes. Hybrid search (Postgres full-text + pgvector), an LLM router with fallbacks, evals in CI, an MCP server. FastAPI, Astro.
Apache-2.0 -
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 -
Multi-agent simulation platform with OMPA memory, a FastAPI service, an MCP server, and optional LLM agents. Portfolio reference (v1 of AegisFlow).
MIT -
A multi-LLM council for Claude Code — convenes Gemini, GPT and Mistral for independent second opinions and cross-model consensus, over MCP.
MIT -
Multi-tenant B2B call analytics platform — LangGraph pipeline, MCP server, pgvector RAG, JWT auth with Postgres Row-Level Security, and automated LLM-as-judge eval harness
-
Open-source enterprise Conversation State Orchestration Platform. Deterministic workflow/state engine for LLM-driven conversations — LLM suggests, State Engine decides. MCP + RAG integrated, multi-tenant, versioned.
MIT ★ 3 -
crosscheck-mcpactive
Multi-LLM MCP server: confer / debate / coordinate / audit / orchestrate across Anthropic + OpenAI + xAI + Gemini + Mistral + Groq + DeepSeek + Kimi + Qwen, with scoreboard-driven router, canary-leak detection, sandboxed shell verifiers, and a tier-aware
npm SEE LICENSE IN LICENSE -
freemodel-mcpgithub.com/yummy342/freemodel-mcpupdated this year
Use the best model for every task — automatically. Multi-provider LLM router for Claude Code. Picks the right model based on what you are doing: coding, writing, reasoning. 25+ platforms (DeepSeek, Qwen, GLM, Gemini, Claude, GPT), one API key. Save 40-70%
npm MIT -
Use the best model for every task — automatically. Multi-provider LLM router for Claude Code. Picks the right model based on what you are doing: coding, writing, reasoning. 25+ platforms (DeepSeek, Qwen, GLM, Gemini, Claude, GPT), one API key. Save 40-70%
npm MIT -
Governed multi-agent memory for AI agents — hybrid markdown+SQLite, FTS, vector search, LLM reranking. One Go binary, MCP stdio + HTTP + SSE.
Apache-2.0 ★ 1 -
@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 -
bonzai-core-enginegithub.com/yethikrishna/bonzai-core-engineupdated this year
Bonzai — AI platform core backend with MCP memory integration. Flask-based API with 26+ blueprints, multi-LLM support (Gemini, OpenAI, Anthropic, DeepSeek), Mem0, CrewAI, Qdrant, Redis.
-
Multi-Agent Autonomous Cybersecurity Platform (Go + LLM) — layered agent orchestration, 91 YAML tool recipes + 50+ built-in MCP tools, HITL safety, single-binary offline deployment.
MIT -
Self-organizing multi-agent platform in Go: LLM agents post, claim, execute and verify tasks. MCP adapter, Claude API, prompt-injection defenses, Telegram operator.
-
Scenario-driven framework for evaluating demographic bias in single- and multi-agent LLM workflows. Tracks bias across sequential stages, separates model non-determinism from systematic effects, and prevents agents inferring evaluation intent. REST API and MCP server.
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