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.
-
nb-agentic-raggithub.com/ydf0509/nb_agentic_ragupdated this year
Agentic RAG MCP Server — 12 tools for AI-driven multi-round code retrieval that outperforms naive single-shot RAG
pypi MIT -
mcp-rag-skills-agentgithub.com/CortexLLMs/mcp-rag-skills-agentupdated this year
MCP RAG Skills Agent - Industrial AI agent combining MCP, RAG, and Skills execution for manufacturing
-
基于 RAG、DeepAgent 与 MCP 的高校奖助学金申请评估智能体|含免费交互 Demo
-
azure-ai-foundry-MAF-RAG-MCP-agentgithub.com/azure-data-ai-hub/azure-ai-foundry-MAF-RAG-MCP-agentupdated this year
—
MIT -
Agentic-RAG-Software-System-Using-MCP-servergithub.com/Deerajsankar/Agentic-RAG-Software-System-Using-MCP-serverupdated this year
—
★ 1 -
中医养生咨询 Agent 平台:垂直领域 RAG + Multi-Agent + MCP Server(Python / LangGraph / chromadb)
MIT ★ 3 -
—
-
r2r-rag-search-agentgithub.com/evgenygurin/r2r-rag-search-agentupdated this year
MCP сервер для интеграции R2R (RAG) с Claude Desktop
-
enterprise-agentic-rag-platformgithub.com/Bhavanaravi07/enterprise-agentic-rag-platformupdated this year
Enterprise agentic RAG platform with hybrid retrieval, MCP tools, guardrails, and observability
MIT -
MCP-powered-Agentic-RAGgithub.com/EimanTahir071/MCP-powered-Agentic-RAGupdated this year
An MCP-powered agentic RAG system that transcribes, indexes, and intelligently queries audio content using advanced retrieval-augmented generation.
★ 3 -
带记忆的 RAG 问答系统:混合检索(55%→100%)+ Agent 记忆 + MCP 插件|FastAPI + Docker + 13 测试
MIT -
RAGv2-Agentic-RAGgithub.com/tumasv1/RAGv2-Agentic-RAGupdated this year
Agentic RAG assistant for a personal Obsidian vault — LangGraph ReAct agent, hybrid search (BM25+dense+reranker), MCP tools, LLM gateway with fallback, Langfuse tracing.
MIT -
Deterministic, namespace-isolated document retrieval with a CLI and MCP server.
npm MIT -
Self-corrective Agentic RAG with LangGraph - eliminates hallucinations through intelligent relevance grading before answering. Features Streamlit UI, MCP server integration & multi-turn memory.
MIT -
Synthetic policy agent with deterministic tools, hybrid retrieval, MCP, and human approval
MIT -
Oyun QA ekipleri için RAG + MCP + ReAct mimarisiyle çalışan otonom AI asistanı — ChromaDB, Trello entegrasyonu, insan onaylı guardrail'ler.
-
hybrid-rag-mcp-agentgithub.com/sharmaranupama/hybrid-rag-mcp-agentupdated this year
RAG system with hybrid search, a ReAct agent, MCP tool exposure, and LLM evaluation
-
A minimal working RAG agent that retrieves context through an MCP (Model Context Protocol) tool server instead of hard-coded retrieval logic.
-
Agent-based Retrieval-Augmented Generation (RAG) chatbot
-
RAG com agentes sobre legislação brasileira: LangGraph, MongoDB Atlas Vector Search, Milvus, Langfuse, Redis, FastAPI e servidor MCP
MIT -
Production-style multi-agent AI system with LangGraph, hybrid RAG, MCP, self-correction, human approval, observability, and RAGAS evaluation
-
Full-stack agentic RAG on Elasticsearch: four retrieval modes behind a read-only MCP server, a decision layer, a CRAG loop and a Pi agent with checked citations, all on local Ollama. 全端 Agentic RAG:決策層、唯讀 MCP 檢索、附來源查核。
MIT ★ 2 -
Agentic RAG research assistant: a LangGraph ReAct agent queries your own documents through a custom MCP server (ChromaDB) and falls back to Tavily web search when the knowledge base lacks the answer.
-
Multi-agent RAG assistant over RBI and SEBI circulars: hybrid FAISS + BM25 search, reranking, cited answers, RAGAS evals and an MCP server
MIT -
An Agentic RAG system built on Model Context Protocol (MCP) to decouple tool execution from agent logic, enabling scalable and modular AI workflows.
★ 2 -
RAG support agent for banking security FAQs — LangGraph, ChromaDB, MCP, LLM-judged faithfulness eval in CI (16/16, p95 1.9s)
-
agentic-rag-mcpgithub.com/enached134-ctrl/agentic-rag-mcpupdated this year
Multi-agent RAG (LangGraph) exposed as an MCP server: plan -> retrieve -> synthesize -> self-critique with citations. Claude + pgvector + Voyage + Firecrawl.
MIT ★ 1 -
multi-agent-raggithub.com/Manthan283/multi-agent-ragupdated this year
Multi-Agent RAG system with FastAPI, FAISS-based retrieval, and MCP-style tool server (Todo + Weather) with JWT authentication and pytest coverage.
-
MCP server that gives a local LLM agentic RAG tools: hybrid search in Qdrant, read-only SQL over tables, calculator and time; Docker Compose
-
Production-grade Corrective & Self-Reflective Agentic RAG Backend powered by FastAPI, LangGraph, PostgreSQL (pgvector), Hybrid Search (RRF), Celery, Redis, and FastMCP.
★ 1 -
A sophisticated Retrieval-Augmented Generation (RAG) system using Model Context Protocol (MCP) with Firecrawl web search and Qdrant vector database. This production-ready implementation features modular architecture, comprehensive error handling, and configurable environments.
-
multi-agent-raggithub.com/olegedly/multi-agent-ragupdated this year
Config-driven multi-agent RAG with LangGraph (Researcher → Critic → Synthesizer), pgvector RAG corpus search, and a SolidJS dashboard. Includes a standalone MCP server for IDE integration. LLM-agnostic, hot-reload dev, docker compose DB.
-
Agentic RAG chatbot over PDF, DOCX, PPTX, CSV and Markdown — multi-agent architecture, MCP-style message passing, source citations, persistent vector store.
MIT ★ 1 -
Sales assistant with Claude tool use, hybrid RAG, prompt caching and an MCP server, measured one change at a time with evals
-
Agentic-RAG-with-MCPgithub.com/j-datta/Agentic-RAG-with-MCPupdated this year
An agentic RAG assistant, built with LangGraph and the Model Context Protocol (MCP), that answers questions from research papers and live web search, served via FastAPI and Docker.
-
GitHub-Documentation-Rag-Agentgithub.com/Mandoa-Labs/GitHub-Documentation-Rag-Agentupdated this year
RAG agent that ingests GitHub's official documentation, embeds it with local Ollama LLMs, and serves semantic search via a PostgreSQL pgvector database.
-
多模态 RAG 智能体:MCP 协议 + GraphRAG + Cross-Encoder 精排 + 多 Agent 编排 + RAGAS 评估
MIT ★ 4 -
rag-mcp-agentgithub.com/BorisTerminator/rag-mcp-agentupdated this year
RAG agent over the Russian Civil Code: 1736 articles chunked into 2543 passages in ChromaDB, exposed to a LangGraph ReAct agent through an MCP tool server. Ships a 20-query evaluation harness with negative tests.
-
Provider-neutral PostgreSQL + pgvector memory with Codex compaction continuity
MIT -
MCP-powered-Agentic-RAGgithub.com/HopeyCodeDS/MCP-powered-Agentic-RAGupdated this year
An Agentic RAG system built on the Model Context Protocol (MCP). Dynamically orchestrates semantic vector context retrieval via a local Qdrant database with an automated Tavily deep-web search fallback engine.
-
Self-correcting agentic RAG on AWS: LangGraph on Amazon Bedrock, S3 Vectors, event-driven Lambda ingestion, ECS Fargate + CloudFront, DynamoDB checkpoints, CDK, OIDC CI/CD gated by evals, MCP server
MIT -
Agentic-RAGgithub.com/Zhonghui-li/Agentic-RAGupdated this year
Slug Advisor — a deployed tool-calling agent for UCSC course advising: LangGraph ReAct, hybrid retrieval (BM25 + pgvector) + reranker, eval-in-CI, Langfuse observability, MCP server, on GCP Cloud Run.
-
An MCP-powered agentic RAG assistant built with FastMCP, Qdrant, BGE-small embeddings, RAG reranking, Gemini generation, evidence verification, and Bright Data web fallback.
★ 1 -
A lightweight agentic RAG-style chatbot and Model Context Protocol (MCP) server that answers questions about LangChain using local vector retrieval, real-time `llms.txt` document resolution, and Corrective RAG (CRAG) context quality evaluation. Built with LangChain, Chroma, Ollama, FastMCP, and Streamlit.
MIT -
An Agentic Retrieval-Augmented Generation (RAG) system leveraging LangGraph for workflow orchestration, MCP for tool integration, and PostgreSQL/pgvector for hybrid information retrieval. It dynamically routes queries across document management, database operations, local document search, and web search, with LLM-based relevance refinement to impro
Apache-2.0 -
Agentic-AI-assistant-with-RAGgithub.com/bangaru-vignesh/Agentic-AI-assistant-with-RAGupdated this year
Agentic AI assistant that combines real-time weather, web research with RAG, and Neo4j graph storage into a single chat-based interface using MCP, FastAPI, Streamlit, and Docker.
★ 1 -
MCP-сервер и RAG для 1С:Предприятия: ИИ (Claude, Cursor, LM Studio, Open WebUI) ищет по коду и метаданным вашей конфигурации, объясняет проведение, движения, заполнение полей, собирает .epf. MCP server for 1C:Enterprise.
MIT ★ 3 -
Physical AI & Humanoid Robotics textbook (8 chapters, Docusaurus, RAG chatbot on Qdrant + Gemini, Urdu localisation) and a full-stack multi-agent todo app (OpenAI Agents SDK, 6-tool MCP server, FastAPI, Next.js, Postgres).
-
secure-rag-multi-agentgithub.com/ssdeanx/secure-rag-multi-agentupdated this year
Secure Retrieval-Augmented Generation (RAG) with role-based access control using Mastra AI orchestration, with JWT Secure, also Deep Research built with Cedar & Next.js. Gemini, OpenAI, Openrouter, & Gemini CLI usable. Also exposes tools, agents as MCP Server Also A2A Agent Cards
NOASSERTION ★ 19 -
mcp-rag-agentgithub.com/luisrodriguesphd/mcp-rag-agentupdated this year
This repository presents a production-ready RAG system combining LangGraph agent with Model Context Protocol (MCP) integration. Features hybrid search using Reciprocal Rank Fusion (RRF) via MongoDB vector and text searches, grounded responses using COSTAR prompting, and automated RAGAS-based evaluation for building reliable, context-aware AI agents
★ 4 -
Real-time-web-search-RAG-with-MCPgithub.com/PranithChowdary/Real-time-web-search-RAG-with-MCPstale
A conversational agent that combines static knowledge (RAG over your docs) with real-time web search using an MCP server.
MIT ★ 5 -
Reproducible RAG & Agent harness: 932-chunk corpus, 30-question frozen eval, 17s zero-API regression gates, self-hosted retrieval/generation/tracing.
-
fbbp-mcp-rag-servergithub.com/changyufei222/fbbp-mcp-rag-serverupdated this year
Provenance-aware MCP retrieval server connecting AI agents to the FBBP RAG knowledge stack.
-
企业级 RAG 知识库问答系统 + AIOps 运维诊断 Agent(Plan-Execute-Replan / LangGraph / MCP)
Apache-2.0 ★ 2 -
Local-first agentic RAG with citations - hybrid search, reranking and multimodal retrieval over your own documents, no database server required - Minimal dependencies
pypi MIT -
Production-style RAG + LangGraph agent for an AI phone receptionist: pgvector, evals with a CI gate, cost/latency logging, LangSmith, MCP server, FastAPI, Docker
-
mcp-rag-bridgegithub.com/zyay/mcp-rag-bridgeupdated this year
MCP server that wraps a RAG knowledge base — query, add, delete documents via any AI agent
MIT -
catastrophes-climatiques-raggithub.com/diegomerchanm/catastrophes-climatiques-ragupdated this year
Agentic climate-risk system - hybrid RAG on IPCC reports + LangGraph agents + MCP server + MLOps, deployed.
MIT -
MCP, RAG and Skills in one Azure agent (Functions MCP server, AI Search, Agent Framework skills), with the governance control per layer. azd up and go.
MIT -
mcp-raggithub.com/dshipley71/mcp-ragupdated this year
Agentic Hybrid RAG Using MCP Servers