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.
-
A hybrid retrieval and MCP server for grounded, tool-using AI agents.
★ 1 -
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
-
Local-first hybrid RAG: LanceDB vector + BM25 with Reciprocal Rank Fusion, exposed as an MCP server. Benchmarked on lexical and semantic queries.
MIT -
hybrid-rag-mcpgithub.com/LynncX/hybrid-rag-mcpupdated this year
a rag mcp supporting for both ways of local model and api . base on https://github.com/shinpr/mcp-local-rag.
MIT ★ 1 -
Local-first hybrid-RAG MCP server (Qdrant + BM25 via RRF), multi-step agent, offline Ollama fallback
MIT -
hybrid-rag-mcpgithub.com/gustavoali/hybrid-rag-mcpupdated this year
Self-hosted RAG service exposed over MCP: hybrid retrieval (BM25 + kNN, RRF fusion) on OpenSearch, multi-provider embeddings, Python 3.11, mypy strict
-
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 -
Hybrid RAG: from-scratch BM25 + dense + RRF benchmarked on BEIR, Claude tool-use agent with citation guardrails, LangGraph workflow, MCP server
-
MCP server exposing hybrid RAG (BM25 + dense + RRF + reranking) over SEC filings — with FastAPI backend, Next.js frontend, and 22-query evaluation.
MIT ★ 2 -
hybrid-graph-raggithub.com/tahasiddiquii/hybrid-graph-ragupdated this year
Hybrid (BM25+dense+RRF) and graph multi-hop retrieval with a labeled benchmark (recall@k/MRR/nDCG) and an MCP connector. Fully offline, zero API keys.
MIT -
hybrid-rag-projectgithub.com/gwyer/hybrid-rag-projectupdated this year
A generalized Retrieval-Augmented Generation (RAG) system with hybrid search capabilities that works with any documents you provide. Combines semantic (dense vector) search and keyword (sparse BM25) search for optimal document retrieval, with an MCP server API for easy integration.
MIT ★ 5 -
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 -
Local code search engine for AI agents: incremental indexer, hybrid retrieval (BM25 + dense embeddings in Qdrant, RSF, per-language reranker) and an MCP server. Tree-sitter chunking, git branch/tag overlays. Java, Kotlin, Groovy, C#, Go, PHP, Python, JS/TS, C/C++, Delphi/Pascal, SQL and more.
Apache-2.0 ★ 2 -
Hybrid RAG system with MCP server — 0.90 RAGAS faithfulness, 0.96 context precision, 91 tests
-
Modular, observable RAG framework exposing tools via MCP (Model Context Protocol) — hybrid search, multimodal ingestion, evaluation, dashboard
MIT -
Teachable RAG pipeline on OneBucket: chunking, hybrid embeddings, LanceDB and an MCP search server
MIT -
study_raggithub.com/jinyangpeng/study_ragupdated this year
基于 LlamaIndex 的企业级 RAG 知识库检索服务,通过 MCP 协议暴露给 AI Agent 调用。多策略检索(Dense/Sparse/Hybrid/Milvus BM25)、能力可插拔、Docker 一键部署。
MIT ★ 4 -
Folio: agentic RAG MCP server with hybrid search, rerank and contextual retrieval on pgvector, behind MCP Gate tokens
MIT -
Pluggable, observable modular RAG service exposed over the Model Context Protocol (MCP): hybrid search, reranking, multimodal ingestion, tracing dashboard and evaluation.
MIT -
fusionpact-vectordbgithub.com/FusionpactTech/fusionpact-vectordbupdated this year
⚡ The Agent-Native Retrieval Engine — Hybrid Vector + Reasoning + Memory for AI Agents. HNSW indexing, tree-based reasoning retrieval, multi-agent orchestration, MCP server, and built-in RAG.
npm Apache-2.0 -
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 -
rag-X-mcp-v1github.com/Sarthak6o1/rag-X-mcp-v1updated this year
MCP-ready RAG monorepo: FastAPI hybrid search, FastMCP tool server, admin upload portal.
Apache-2.0 -
Production-grade Corrective & Self-Reflective Agentic RAG Backend powered by FastAPI, LangGraph, PostgreSQL (pgvector), Hybrid Search (RRF), Celery, Redis, and FastMCP.
★ 1 -
Local-first multimodal RAG assistant (FastAPI + React) — hybrid retrieval, HyDE, cross-encoder reranking, and an MCP server for querying your documents from Claude Desktop.
-
content-raggithub.com/Awis13/content-ragupdated this year
Local-first RAG service with glass-box hybrid retrieval (pgvector + Postgres FTS + RRF), cited answers, RAGAS eval, and an MCP server. Flask + Ollama, fully Dockerised.
MIT -
RAG pipeline for documents (Markdown, PDF, images). 10-step hybrid search, LLM enrichment, taxonomy, MCP server. Cloud or local.
NOASSERTION ★ 4 -
RAG knowledge retrieval for autonomous driving R&D — BM25 + Dense hybrid search, metadata boost, MCP server, Streamlit dashboard. | 面向自动驾驶的 RAG 知识检索系统,支持算法文档、测试规范、问题案例检索。
MIT -
mcp-playgroundgithub.com/marek5050/mcp-playgroundupdated this year
Oauth MCP server with hybrid search RAG capability.
MIT -
biomedical-rag-research-assistantgithub.com/Electrolight123/biomedical-rag-research-assistantactive
Biomedical RAG assistant for PubMed documents featuring hybrid ChromaDB and BM25 retrieval, MiniLM embeddings, RRF, grounded citations, guardrails, MCP tools, FastAPI, Streamlit, Langfuse, RAGAS, and automated evaluation.
★ 1 -
Local-first, offline-capable Agent memory & knowledge service. REST + MCP dual-protocol, hybrid retrieval (vector + BM25/RRF), document/webpage RAG. No LLM required for storage & retrieval
pypi Apache-2.0 ★ 5 -
code-rag-mcpgithub.com/pawankhatri584/code-rag-mcpupdated this year
Lightweight repo-local hybrid (semantic + keyword) code search over MCP. No Docker, no Ollama, no servers. 11 languages, live watcher. Install: npx code-rag-mcp init
npm MIT -
Universal-file-RAGgithub.com/ankitjswl56/Universal-file-RAGupdated this year
Hybrid RAG over PDFs, DOCX, spreadsheets, code repos, audio & images — explainable per-file retrieval routing (vector/hierarchical/code-graph), cited answers, and an MCP server. Powered by Gemini.
-
TypeScript knowledge graph RAG for AI agents: source evidence, hybrid retrieval, MCP integration, and a permission-aware PostgreSQL runtime.
Apache-2.0 ★ 31 -
Local-first RAG engine with hybrid search, BGE reranker, self-learning loop, and MCP server
-
Local-first RAG engine built on the Laya decision engine: hybrid BM25 + dense recall, calibrated relevance re-ranking and answerability gating that return evidence with probabilities rather than generated prose. CLI, FastAPI HTTP API, MCP server and web GUI.
Apache-2.0 -
Pharos — local-first agentic RAG for your team's document library: multi-format ingest, hybrid retrieval, enterprise ACL, dual HTTP + MCP exits.
MIT ★ 241 -
flowsim-tutorgithub.com/Ahmed-Hassan-portfolio/flowsim-tutorupdated this year
Hybrid RAG + MCP documentation tutor with Chainlit UI, workflow memory, synthetic docs, and multi-server orchestration.
MIT -
knowledge-base-mcpgithub.com/gaztrabisme/knowledge-base-mcpupdated this year
Local MCP server for hybrid semantic search over your own documents — bring-your-own-corpus RAG for Claude Code.
Apache-2.0 -
mcp-pgvector-searchgithub.com/JuanPinilla198/mcp-pgvector-searchupdated this year
Hybrid RAG over pgvector, exposed as MCP tools — semantic and keyword search fused with Reciprocal Rank Fusion
MIT -
Local RAG workspace with persistent documents, hybrid search, reranking, cited answers, FastAPI, MCP and LangChain.
-
Sanitized public extract of a private podcast RAG system in daily use. Hybrid retrieval (BM25 + dense embeddings, RRF fusion) with a 122-query gold-set eval (recall@k, MRR) gated in CI, passages cited to the minute, served over a typed MCP interface.
MIT -
Autonomous RAG Knowledge Architecture, Semantic Chunking, Vector Embeddings & Hybrid Search MCP for Cursor, Claude & Windsurf
-
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 -
mcp-raggithub.com/dshipley71/mcp-ragupdated this year
Agentic Hybrid RAG Using MCP Servers
-
Local hybrid-search RAG (SQLite FTS5 + Ollama embeddings, weighted RRF) over your own project notes, served to Claude Code as an MCP server
MIT -
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 -
MedQuerygithub.com/kikugo/MedQueryupdated this year
Medical Q&A assistant using hybrid RAG (BM25 + FAISS with RRF) over MSF Essential Drugs guidelines, with agentic mode, evaluation suite, and MCP tools.
-
Local RAG server for Claude Code, Cursor and other MCP clients: hybrid BM25 + vector search with cross-encoder reranking on by default, 13 MCP tools, 33 file types including code, re-indexing on file changes. One Python process with embedded ChromaDB and FastEmbed ONNX: no Docker, database server or API key; offline after the first model download.
npm MIT ★ 306 -
opencode-memorygithub.com/xpajonx/opencode-memoryupdated this year
Distributed local-first hybrid-RAG memory layer and Harness bootstrapper for opencode agents, with dynamic pre-injection and styled console TUI.
★ 1 -
Personal unified memory system for AI agents. SQLite-backed, local-first, hybrid RAG retrieval with MCP integration.
MIT ★ 1 -
Paper research assistant with hybrid RAG, source-grounded QA, field-level evidence and tool-calling agents. 多源检索、可溯源问答与跨论文比较(Web / CLI / MCP)。
-
gleangithub.com/gleean/gleanupdated this year
A local-first knowledge engine and RAG infrastructure powered by Rust, featuring MCP support, hybrid search (BM25 + Vector), and LanceDB integration
Apache-2.0 ★ 1 -
vectorize-mcp-workergithub.com/dannwaneri/vectorize-mcp-workerupdated this year
Hybrid RAG Worker on Cloudflare Edge — Vector + BM25 search, metadata filtering, multimodal vision, MCP server, and intelligent query routing. ~400ms p99.
MIT ★ 28 -
Self-hosted research assistant: hybrid RAG (BM25 + vectors) with verifiable citations, grounded AI briefs, eval harness, MCP server. Runs free with Groq + local embeddings.
MIT -
Lightweight Model Context Protocol (MCP) bridge and hybrid sync engine connecting Notion workspaces with AI agents and vector RAG pipelines.
pypi MIT -
amanmcpgithub.com/Aman-CERP/amanmcpupdated this year
AmanMCP is a local-first RAG MCP server for developers - providing hybrid search (BM25 + semantic) over codebases for AI assistants like Claude Code and Cursor.
go Apache-2.0 ★ 4 -
Open-source Rust multimodal vector database & RAG platform: one unified space for text, image, audio, video & docs - hybrid search, reranking, built-in MCP server.
AGPL-3.0 -
Production-oriented AI case investigation platform with Hybrid RAG, Agentic AI, MCP, HITL, Azure, AWS, FastAPI, React, PostgreSQL, and pgvector.
MIT -
Built an agent using LangChain, Hybrid RAG, SurrealDB memory, and GitHub MCP tools, Django, capable of answering repository-specific questions through vector search, graph retrieval, and live GitHub metadata. Exposed the agent as an MCP server for A2A communication with any external AI agents through a standardized MCP client.
-
Local-first memory, hybrid RAG, and agent personalization for AI coding agents. MCP + CLI for OpenCode, Codex, Claude Code, Gemini CLI, and Antigravity.
npm MIT ★ 2