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 descriptions, licences and links are read from each package's own registry (npm, PyPI, crates.io, NuGet, RubyGems; Go and Maven packages are only checked to exist). Packages are found through ecosyste.ms; its metadata (CC BY-SA 4.0) is kept only where the registry could not be read, and packages the registry no longer has are removed. 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-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 -
dhm-hybridgithub.com/emircbngl/dhm-hybridupdated this year
Open-source digital holographic microscopy (DHM) workstation: off-axis hologram reconstruction, quantitative phase imaging, autofocus, and reference-free phase retrieval via a hybrid classical + CNN pipeline. PySide6 GUI, optional Apple Silicon MLX acceleration, and an MCP server for AI agents.
Apache-2.0 ★ 1 -
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 -
mcp-knowledge-servicegithub.com/hyh0620/mcp-knowledge-serviceupdated this year
Reusable MCP-based knowledge retrieval service with ingestion, Hybrid Retrieval, citations, and collection-based isolation.
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 -
A RAG agent that grades its own retrieval, reformulates the query when confidence is low, and abstains instead of hallucinating. LangGraph + hybrid search + reranking, served over MCP, measured against two naive-RAG baselines with an LLM-as-judge harness and RAGAS.
MIT -
Wenmai Search — self-hosted, traceable hybrid document retrieval with REST, MCP, and Web UI
MIT ★ 3 -
Memory system for AI agents with hybrid retrieval, MCP tooling, and LongMemEval-leading performance.
NOASSERTION ★ 3 -
Folio: agentic RAG MCP server with hybrid search, rerank and contextual retrieval on pgvector, behind MCP Gate tokens
MIT -
ClariRAGgithub.com/AaronFChristian/ClariRAGupdated this year
Production-grade Agentic RAG over clinical guidelines - Hybrid retrieval, LangGraph, Citations, MCP Server
-
An MCP server that gives any LLM host grounded, cited retrieval over your own documents — hybrid BM25 + dense retrieval, cross-encoder-ready reranking, and built-in eval.
npm MIT -
AdaptiveRAG: An evaluated, version-aware retrieval-augmented generation system with hybrid search, evidence verification, and distributed services.
-
Private hybrid search over your files, running on your machine, 70+ languages. An MCP retrieval backend for AI agents.
Apache-2.0 ★ 1 -
Agent-agnostic code-intelligence and safe-validation backend with hybrid retrieval, file:line citations, and MCP agent integration.
pypi LicenseRef-Proprietary -
MCP server over NIST SP 800-53 with hybrid retrieval, verified citations and an eval-gated CI pipeline.
MIT -
TypeScript knowledge graph RAG for AI agents: source evidence, hybrid retrieval, MCP integration, and a permission-aware PostgreSQL runtime.
Apache-2.0 ★ 31 -
engineering-knowledgegithub.com/bienherasme/engineering-knowledgeupdated this year
Local-first engineering knowledge retrieval with deterministic ingestion, provenance, hybrid search, reproducible evaluation, CLI, and read-only MCP.
MIT -
etAIgithub.com/ectdev/etAIactive
Grounded search and cited answers over a folder of markdown: hybrid retrieval, a citation gate, measured refusals, and an MCP server.
MIT -
Local-first multimodal RAG assistant (FastAPI + React) — hybrid retrieval, HyDE, cross-encoder reranking, and an MCP server for querying your documents from Claude Desktop.
-
Local OpenAI-compatible embeddings and reranking on Apple Silicon: bge-m3 hybrid search, Qwen3, a retrieval eval harness and MCP memory for agents.
MIT ★ 1 -
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 -
Local-first MCP server for searching private Obsidian vaults with hybrid full-text, fuzzy, semantic, and wikilink graph retrieval. Runs locally via Node/npm; only the vault path is required.
smithery -
MCPgithub.com/Diluksha-Upeka/MCPupdated this year
Production-ready Enterprise MCP Operations Console featuring secure AI agent workflows, human-in-the-loop approvals, hybrid retrieval, and enterprise-grade authentication.
MIT -
Hybrid product search over 43k messy real-world listings (Wayfair WANDS), with BM25 + vector retrieval, reranking, measured evals, and an MCP server so Claude or ChatGPT can query it.
-
Codebase Intelligence Engine & MCP Server — AST semantic chunking, tri-hybrid retrieval (BM25 + vectors + graph), and grounded LLM synthesis for any repository.
npm MIT -
MCP server for LanceDB-backed long-term memory with hybrid retrieval (Vector + BM25), cross-encoder rerank, multi-scope isolation, and memory lifecycle management
npm MIT -
ostk-recallgithub.com/os-tack/ostk-recallupdated this year
Local-first cross-corpus retrieval MCP server — model2vec embeddings + LanceDB (Tantivy BM25) + SQLite. One binary; hybrid (dense + BM25) search across markdown, code, and Claude Code sessions.
Apache-2.0 ★ 6 -
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
-
ContextAtlasgithub.com/codefromkarl/ContextAtlasupdated this year
ContextAtlas — context infrastructure for AI coding agents: hybrid retrieval, project memory and retrieval observability via CLI, MCP server or embeddable library. Tree-sitter indexing, LanceDB vector search, FTS5 and token-aware context packing.
npm MIT ★ 30 -
context-bridge-mcpgithub.com/tijuthomas5/context-bridge-mcpupdated this year
A local-first code retrieval MCP server for AI coding agents. Hybrid keyword + vector search over Graphify-indexed codebases, with domain-aware ranking profiles.
NOASSERTION ★ 3 -
contextweaver-mcpgithub.com/wchiway/contextweaver-mcpupdated this year
Semantic code retrieval engine for AI coding agents, with hybrid search, AST-aware chunking, graph expansion, and token-aware context packing.
npm MIT ★ 2 -
Long-context project memory for MCP hosts, measured on Claude Code — a local MCP server with hybrid retrieval (dense + BM25 + cross-encoder rerank). Falsification-first benchmarks, honest nulls.
MIT -
Portable hybrid (BM25 + dense + RRF) retrieval engine and a label-free evaluation harness — extracted from a personal AI-assistant memory index and decoupled to run on any source tree.
pypi MIT ★ 4 -
Intent-first search that finds the right tool from a vague description. Hybrid retrieval over LLM-written cards, LLM rerank with recall safety, MCP server for AI agents, runs on a laptop CPU.
MIT ★ 1 -
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 -
MCP server giving AI assistants cited access to official statistics (SDMX) and policy documents (hybrid RAG: keywords plus embeddings), with a sensitivity ceiling and a retrieval evaluation as a CI gate.
MIT -
Grounded, auditable context layer for enterprise agents: a deterministic path for exact facts + Elasticsearch hybrid retrieval for exploration, exposed over MCP. Every answer carries its provenance; refuses when it can't ground. Model-agnostic (Claude, Codex, Antigravity).
MIT ★ 1 -
MCP-Memory-LanceDB-Progithub.com/bcornish1797/MCP-Memory-LanceDB-Proupdated this year
Full memory-lancedb-pro memory enhancement system for Claude Code via MCP protocol — hybrid retrieval, smart extraction, auto-capture, intelligent forgetting, multi-scope isolation. Feature parity with OpenClaw memory-lancedb-pro plugin.
npm MIT -
resolvegithub.com/SamueleOlindo/resolveupdated this year
Evidence-first technical-support agent. Hybrid RAG (dense + BM25 + Reciprocal Rank Fusion), an agentic LangGraph workflow that self-corrects, and deterministic citation validation. Retrieval evaluation (Recall@k, MRR, nDCG), FastAPI, React, MCP server, Docker, Groq LLM.
-
irishpulsegithub.com/S-Shetty/irishpulseupdated this year
Multi-agent EU AI Act compliance system for Irish SMEs. LangGraph orchestrator routes queries across 3 specialist agents (ReAct, RAG, Tree-of-Thought). ChromaDB + BM25 hybrid retrieval, RAGAS eval gates, Langfuse tracing, Kafka news pipeline, MCP server.
-
Grounded, auditable context layer for enterprise agents: a deterministic path for exact facts + Elasticsearch hybrid retrieval for exploration, exposed over MCP. Every answer carries its provenance; refuses when it can't ground. Java/Spring implementation of the same spec; model-agnostic MCP interface.
MIT -
Local document retrieval with hybrid search, MCP tools and a Streamlit dashboard.
MIT -
Hybrid-retrieval memory layer for AI agents: Qdrant + SQLite FTS5 + RRF, with REST and MCP.
pypi Apache-2.0 -
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 -
Retrieval-augmented Q&A over your docs: hybrid pgvector + Postgres full-text search with reciprocal rank fusion, validated citations, retrieval evals gating CI, and an MCP server. Python, FastAPI, LangChain splitters, local embeddings.
MIT -
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 -
Islamic texts (Hadith & Tafsir) hybrid retrieval engine and Model Context Protocol (MCP) server combining ChromaDB semantic search and SQLite FTS5
-
RAG3github.com/nyamx/RAG3active
Local document search with GPU-aware ingestion, hybrid retrieval, desktop UI, and MCP access from Codex and ChatGPT web.
MIT -
MCP server for searching motorcycle manuals with hybrid retrieval and calculating maintenance intervals.
MIT -
Python code intelligence with source parsing, code-graph indexing, PostgreSQL/pgvector storage, hybrid retrieval, and CLI, HTTP, and MCP interfaces.
-
books_raggithub.com/zcoderz/books_ragupdated this year
Precision-first RAG engine for technical books — hybrid retrieval, reranking, citation-backed answers with abstention, 34 MCP tools
Apache-2.0 ★ 1 -
Hybrid retrieval and RAG over research files, with source tracing, reviewable file operations, MCP tools, and reproducible ranking benchmarks.
Apache-2.0 -
AzureAISearchMCPgithub.com/HeyJiqingCode/AzureAISearchMCPupdated this year
MCP server for Azure AI Search, supporting keyword, semantic, vector, hybrid, and Knowledge Base agentic retrieval.
MIT ★ 2 -
Hybrid retrieval over a markdown vault, served as an MCP server: FTS5 and sqlite-vec fused by rank, then a cross-encoder reranker. One SQLite file.
MIT -
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 -
Personal unified memory system for AI agents. SQLite-backed, local-first, hybrid RAG retrieval with MCP integration.
MIT ★ 1 -
Local hybrid search over an Obsidian vault for Claude Code via MCP: on-device embeddings, BM25 + vector rank fusion, incremental sync, measured retrieval.
MIT -
Self-hosted private-code context layer for AI coding agents, with MCP tools, citations, tenant boundaries and hybrid retrieval
Apache-2.0 -
Semantic search for your Telegram chats — fully local hybrid retrieval, MCP server + CLI for any AI agent
MIT ★ 2