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.
-
a RAG with qdrant as MCP with Web-UI
-
rag-qdrant-voyagegithub.com/mattmagg/agentic-rag-sdkupdated this year
Agentic RAG SDK - MCP server for grounding AI coding agents with Voyage AI + Qdrant hybrid retrieval
pypi MIT -
qdrant-loader-mcp-servergithub.com/martin-papy/qdrant-loaderupdated this year
A Model Context Protocol (MCP) server that provides RAG capabilities to Cursor using Qdrant.
pypi GPL-3.0 -
Local help-desk RAG: hybrid retrieval, reranking, evals, tracing and an MCP tool, all on a laptop (Ollama, Qdrant, Phoenix)
MIT -
@ygen-phoenix/rag-mcpupdated this year
MCP server that exposes Qdrant + Ollama as RAG tools (list_collections, search_collection, answer_question) over stdio.
npm MIT -
@ygen-phoenix-kb/phoenix-rag-mcpupdated this year
MCP server that exposes Qdrant + Ollama as RAG tools (list_collections, search_collection, answer_question) over stdio.
npm MIT -
MCP server combining Qdrant vector search, Neo4j knowledge graphs, and Crawl4AI web intelligence with agentic RAG capabilities. FastMCP 2.0 architecture with enterprise security, monitoring, and Kubernetes deployment. AI/ML engineering powerhouse.
MIT ★ 9 -
TFG (9.90/10): RAG + MCP chatbot ecosystem for the Erasmus+ office at the University of Huelva. n8n, Qdrant, PostgreSQL, Ollama, Docker.
-
Production-grade RAG pipeline for accounting professionals — hybrid retrieval (vector + BM25), SSE streaming, multi-user auth, semantic caching, MCP server. FastAPI + Qdrant + Cerebras.
MIT ★ 1 -
Local-first hybrid-RAG MCP server (Qdrant + BM25 via RRF), multi-step agent, offline Ollama fallback
MIT -
MCP server that gives a local LLM agentic RAG tools: hybrid search in Qdrant, read-only SQL over tables, calculator and time; Docker Compose
-
MCPulse-RAGgithub.com/ODO-TECH/MCPulse-RAGupdated this year
Self-hosted RAG stack with Qdrant, MCP over SSE, automatic indexing, file watching, scheduled health checks, and email reporting.
MIT ★ 1 -
domain-rag-mcp-serveractive
MCP server for domain RAG search — connects to Qdrant + PostgreSQL + Code Search API for hybrid search across Jira, Confluence, Git commits, and server-side code repositories
npm -
ragify-mcpgithub.com/strawberry-code/self-hosted-llm-ragupdated this year
MCP Server for RAG documentation search with Qdrant and Ollama
pypi MIT -
RAGGuard: check that your RAG index matches your source documents. Finds missing, stale, duplicate, deleted-but-searchable and wrong-tenant chunks in Qdrant and pgvector. CLI and MCP server included.
pypi MIT -
A-Multi-Source-Research-Intelligence-Platform-with-MCP-and-Hybrid-RAGgithub.com/GunaTeja777/A-Multi-Source-Research-Intelligence-Platform-with-MCP-and-Hybrid-RAGupdated this year
Production-grade academic research assistant using Hybrid RAG, MCP, LangGraph & Qdrant — with self-correcting citation guardrails and sub-2s P99 latency.
★ 3 -
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-hosted RAG knowledge base for AI coding assistants. MCP server with Qdrant + Ollama embeddings.
MIT -
Code RAG MCP server: semantic indexing and retrieval of a local codebase (declaration-aware chunking + bge-m3 embeddings + Qdrant hybrid search). Exposes search_code / index_codebase / index_status / index_cancel / set_root MCP tools and a CLI, plus a loc
npm MIT -
Mnē-MCP — MCP server de RAG para opencode: indexa vaults de Obsidian, embeddings bge-m3 locales (Ollama), Qdrant vectorial y respuestas fundamentadas con deepseek-v4-flash citando la fuente exacta.
-
TicketingAIgithub.com/brahimusgmail/TicketingAIupdated this year
Modern Ticket Management System built with .NET 10, Blazor, Clean Architecture, SQL Server and AI (RAG, MCP, Qdrant).
MIT -
Production multimodal enterprise search & Corrective RAG (CRAG) platform. 5-agent LangGraph orchestration, dynamic query rewriting, Docling layout parsing, Groq Whisper-v3, Qdrant hybrid search, and NeMo guardrails. 298 tests.
MIT -
Pipeline dữ liệu thô cho AI Agent: ingestion đa định dạng, chunking, Qdrant, agentic RAG (LangGraph), MCP bridge
-
AI integration layer for NodeBB forums with MCP, semantic search, RAG and Qdrant knowledge pipeline
npm MIT -
claude-lfr-mcphttps://gitlab.com/derico/claude-lfr-mcpupdated this year
Fast CPU-based RAG for codebases using BGE embeddings and Qdrant. MCP server for Claude Code.
pypi MIT -
FieldForge AI Suite: grounded RAG Q&A, human-supervised incident agent, A2A/MCP agent mesh, LLMOps quality gate, offline edge profile (FastAPI, Qdrant, Ollama)
NOASSERTION -
Prototipo académico de un agente de IA para ventas e inventario con RAG, Qdrant, Gemini, FastAPI, Streamlit y MCP.
-
Ollqdgithub.com/leomarviegas/Ollqdupdated this year
MCP client-server RAG system — index codebases & documents into Qdrant using Ollama embeddings, with code-aware chunking and interactive chat
Apache-2.0 -
akopiagithub.com/rlabs-cl/akopiaupdated this year
Plug. Sync. Serve. — headless retrieval plane for your AI stack. Self-hosted RAG infra with Qdrant + Meilisearch + Redis, plugin-first, MCP-native.
MIT -
MCP server for RAG indexing, hybrid search, and generation of PDF/Excel/Word documents — powered by Mistral (OCR + embeddings) and Qdrant.
AGPL-3.0 -
Fork of xiaozhi-esp32-server for ESP32 voice assistants, extended by MekongAI with voiceprint recognition, RAG + Qdrant and a CLI dashboard. Python/Java/Vue, MQTT + WebSocket, MCP.
MIT -
semantic-code-searchgithub.com/n1ra7/semantic-code-searchupdated this year
Self-hosted, zero-cost semantic code search + RAG with an MCP server — FastEmbed embeddings, Qdrant vector DB, incremental indexing, and eval harness. Python.
MIT -
Multi-tenant RAG and MCP document intelligence platform with secure PDF ingestion, tenant-isolated Qdrant retrieval, Groq-powered grounded answers, and a Flask web application.
-
flight-report-agentgithub.com/juandagalo/flight-report-agentupdated this year
Multi-provider LLM travel recommendation agent with RAG-enhanced suggestions, Qdrant vector search, MCP server, and Claude Code integration. Generates comparative PDF reports with real flight data.
-
llm-wikigithub.com/shin-client/llm-wikiupdated this year
A blazing-fast, event-driven RAG pipeline and MCP Server built in Rust. Automatically sync local Markdown notes to Qdrant and make them semantically searchable for AI coding assistants like Cursor and GitHub Copilot.
MIT -
Document intelligence service: upload docs, search by meaning, get cited answers from a local LLM (RAG), exposed to AI assistants via MCP. FastAPI, Qdrant, Postgres, Ollama, sentence-transformers, LangSmith.
-
grounded-kbgithub.com/smastracci/grounded-kbupdated this year
Provenance-tracked RAG service exposed as an MCP server with a LangGraph tool-calling agent. Grounded citations, a machine-checkable refusal contract, and a self-measuring evaluation harness. Dagster ingestion, Qdrant retrieval, FastAPI serving.
MIT -
Document Q&A platform with RAG — upload PDFs, ask questions, get grounded answers with sources. Built with FastAPI, Celery, Redis, Qdrant, and Ollama, plus a Model Context Protocol (MCP) server.
-
datamindgithub.com/rakmohan/datamindupdated this year
Agentic data catalog platform — scans PostgreSQL/BigQuery, auto-classifies PII/PCI/PHI, scores data quality, and generates business definitions using LLM + RAG. Built with LangGraph, FastAPI, Qdrant, and ▎ FastMCP. Exposes catalog intelligence as MCP tools for AI agents.
MIT -
rag-mcpgithub.com/ryddle/rag-mcpupdated this year
A Model Context Protocol (MCP) server that provides RAG (Retrieval-Augmented Generation) capabilities using local embeddings and Qdrant vector database.
-
A CLI tool for personal RAG that retrieves data from Notion, Obsidian, Apple Notes, etc., stored in Qdrant and exposed as an MCP server.
★ 6 -
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.
-
Self-hosted SDLC context graph + RAG over GitLab & GitHub repos: code graph (definitions, imports), MR diffs, CI, planning, security — served to AI agents via MCP. A free, lightweight OSS alternative to GitLab Orbit (Qdrant + NATS; no ClickHouse/K8s).
MIT -
Self-contained MCP server for Rag.NET, configured entirely via appsettings.json or environment variables — an OpenAI-compatible chat/embedding endpoint plus InMemory, Qdrant, or PgVector.
nuget MIT -
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 -
Production-grade hybrid RAG in TypeScript — vector + BM25 + reranker across 14 vector stores (Qdrant, Pinecone, Weaviate, pgvector, LanceDB & more) behind one adapter API. Benchmarked chunking, eval datasets, ablation studies & an MCP server. Not a toy.
MIT ★ 1 -
Policy MCP server (Go) — Qdrant RAG policy enforcement with fail-closed design
NOASSERTION -
clinical-raggithub.com/stel-nik/clinical-ragupdated this year
Private on-prem RAG system for clinical document Q&A. Chunks, embeds, and retrieves using local models only. No data leaves the network. Includes an MCP server for AI agent integration and a private Llama3.1 agent. Built for regulated environments: FastAPI, Qdrant, Ollama, Docker, Kubernetes.
MIT -
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).
-
quorumgithub.com/danielhansenjones/quorumupdated this year
Multi-agent RAG system on LangGraph: parallel per-axis analyst agents over hybrid retrieval (Qdrant, BGE-M3) and Postgres, a tool-using critic for claim-level fact-checking, MCP server, and an eval harness with A/B campaigns and a QLoRA-distilled local judge.
MIT -
claude-lfr-mcpgithub.com/MrTango/claude-lfr-mcpupdated this year
Fast CPU-based RAG / Search for codebases using BGE embeddings and Qdrant. MCP server for Claude Code.
MIT -
MCP server for per-customer PDF document management and RAG. Ingests text, scanned and chart-heavy PDFs (PyMuPDF + Tesseract + vision model), isolates each customer in its own Qdrant collection, and returns cited answers with deep links to the original PDF page. Local-first with Ollama, or any OpenAI-compatible API.
MIT -
enterprise-agentic-ai-platformgithub.com/rathinGithub/enterprise-agentic-ai-platformupdated this year
Production-ready Enterprise Agentic AI Platform built with Spring AI 2.0, Java 21, MCP, RAG, Qdrant, OpenTelemetry, and enterprise-grade architecture.
MIT ★ 1 -
AI_Chat_botgithub.com/2003Grace/AI_Chat_botupdated this year
An intelligent multilingual WhatsApp travel assistant for a Travel Agency, powered by LLMs (Gemini), MCP tools, and Retrieval-Augmented Generation (RAG) with Qdrant.
-
MCP server for AI agents to evaluate GitHub repos — health scoring, commit summaries, mislabeled good-first-issue detection, and embeddings-based RAG Q&A (Voyage AI + Qdrant)
npm MIT ★ 1 -
Antigravity_Optimizer_MCPgithub.com/Dimokat/Antigravity_Optimizer_MCPupdated this year
A local RAG-powered Model Context Protocol (MCP) server using Qdrant and FastEmbed to help AI coding agents navigate, understand, and optimize large codebases.
MIT ★ 3 -
Living Digital Twin for Disaster Recovery: Neo4j graph + VictoriaMetrics + Qdrant RAG + FastAPI MCP Server + React 3D dashboard
-
FastAPI-based backend for a Healthcare Appointment Booking system using Model Context Protocol (MCP) tools. Features include AI-driven RAG-based recommendations, user and professional management, PDF uploads, and scalable data handling with MongoDB, Redis, Qdrant, and Gemini.
-
Self-hosted RAG stack for crawl, scrape, search, ingest, query, and ask workflows with Qdrant, TEI embeddings, Chrome rendering, MCP/CLI/REST, and Gemini synthesis.
AGPL-3.0 ★ 4 -
Sovereign agentic AI platform: Groq + Gemini gateway with auto model detection, hybrid RAG (Qdrant), temporal graph, LangGraph agent swarm, CNN vision, MCP server and zero-trust security. FastAPI, Docker, Kubernetes.
MIT ★ 1