- Conduid
- Marketplace
- #bm25
MCP servers tagged bm25
162 live MCP servers tagged "bm25", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with bm25.
Axis Knowledge Rag
軸メタデータ × ベクトル検索 × BM25 の 3-way hybrid RAG OSS。日本語ナレッジ特化、MCP server 対応、LangChain 不使用の自前実装。
Mcpdoc Rust
🚀 High-performance Rust MCP server for llms.txt documentation with BM25 search. 50x faster startup than Python, single binary deployment, persistent caching, and cross-platform su…
Lira MCP
MCP server over the Liara cloud documentation: hybrid Persian/English retrieval, page reads, deployment config and build-log diagnosis. Corpus ships in the package, so no ingest,…
AI MemoryHub
零依赖确定性 Agent 长期记忆系统 — Markdown 权威源 + 薄索引，拒答/澄清替代向量硬猜，玻璃盒可审计。 | Zero-dependency deterministic agent memory system — Markdown authoritative store + thin index, refuse/clarify instea…
Local AI Lab
Hands-on course for building local, private AI from scratch - RAG, MCP, LangChain, LangGraph. Runs on your machine (Python, Node.js & C#) with Claude Code, Ollama, Gemini, or Open…
Document Buddy
Serverless MCP toolkit for Feishu/Lark project memory: turn docs, wiki pages, chats, meeting notes, PDFs and web snippets into cited LLM wiki answers.
Stackline Tool Router
Local, zero-dependency AI tool discovery for MCP, OpenAI, Anthropic, and Gemini catalogs
Memoryvault Kit
A personal memory layer for your AI tools. Intelligent authoring (gap detection, self-enriching graph, session-synthesis loop) + measurably good retrieval (94.9% blind Cov@10, sub…
LLM Wikimind
The production-ready implementation of Karpathy's LLM Wiki pattern. Markdown + BM25 + MCP. No embeddings, no vector DB.
Pi Zgrep
Semantic code search for the pi coding agent. One tool, four routes (hybrid, BM25, vector, ripgrep), auto-indexed. Powered by zg.
Keyword Rag MCP
MCP Knowledge Retrieval Server: 토스 결제연동 MCP 프로젝트를 참고하여 BM25 알고리즘 기반으로 마크다운 문서를 검색하고 지식 검색을 제공하는 MCP 서버입니다.
Plugmem
Embedded bitemporal memory engine with hybrid retrieval for local-first applications and AI agents — in-process, no server.
Topk
Topk — independent third-party profile of a public API surface, by API Evangelist. TopK is a search engine for accuracy-critical AI applications, delivering hybrid search, multi-v…
Concept Router
A zero-infra MCP server that turns an Open Knowledge Format (OKF) bundle into fast, lexical-first knowledge discovery for LLM agents — no vector DB, no embeddings by default.
Legal Workspace MCP
MCP server that gives Claude self-updating access to a local document directory. TF-IDF search, live file watching, PDF/DOCX/MD support. Built for legal workflows, works with any…
Second Brain CLI
A Rust CLI for RAG - indexing markdown notes with local vector embeddings and exposing them to AI assistants via MCP (Model Context Protocol).
Picoqmd
Lightweight QMD alternative: fully local hybrid search engine (BM25 + vector + rerank) and MCP server in a single ~15MB Go binary. No Node.js. Runs on Raspberry Pi.
Mdya
Small, fast retrieval primitive for local Markdown — FTS + on-device vector search + MCP server. local-first, no cloud.
Duxxdb
The database built for AI agents - hybrid vector + BM25 + structured, durable, with RESP / MCP / gRPC servers. Apache 2.0.
Homebrew Amanmcp
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.
Bert
Long-context project memory for Claude Code / Cursor / Codex — a local MCP server with hybrid retrieval (dense + BM25 + cross-encoder rerank). Falsification-first benchmarks, hone…
Pinakes
Pinakes — a portable, agent-first knowledge base. One directory = one KB.
Yojaka AI Profile Matching Engine
Intelligent AI Recruiter Assistant - Agentic Profile Matching Engine with LangGraph State Machine, MCP Dual Gateway, Hybrid RAG, and Async Task Infrastructure.
Wikillm Digest NoLLM
Research paper PDF to grounded WikiLLM source Markdown, without an LLM. Layout-aware deterministic compiler with a verified verbatim grounding audit.
Insight MCP
Self-contained MCP server for hybrid document search (BM25 + dense RRF) — retrieval-only, works out of the box, Prometheus metrics, Docker, CI/CD
Note AI Assistant
An unofficial, local AI chat app for Obsidian — search and edit your notes by chatting. In-process RAG (embeddings + BM25 + RRF), powered by the Cerebras / Ollama Cloud APIs.
Anydocs
MCP server for fast BM25 search across coding-agent docs (Claude Code, Codex, Cursor, opencode, xAI). ~500 tokens a search, runs locally, no API key.
Memory Lattice
Best AI Memory Layer for Claude Code and MCP Agents in 2026
Spelunk
Hybrid semantic code retrieval engine in Rust - lexical + embedding search for finding code by meaning
SentinelRAG
A policy-aware hybrid RAG agent for secure question answering over code repositories and documentation, with BM25/FAISS retrieval, MCP-style tool routing, and multi-model evaluati…
Webdocs MCP
Crawl, index, and hybrid-search documentation sites; served to LLM agents as an MCP server. FastAPI + DuckDB + BM25/embeddings, fully offline-testable.
Apexgraph
Apex-relevance subgraph retrieval for AI agents — feed your LLM the most relevant slice of a knowledge graph, within a token budget.
OpenContextScitool
LLM context handler over an Open Knowledge Format bundle BM25 search via MCP, usage telemetry, and a health dashboard. No embeddings, no API key.
Sts X
STS-X - an AI-Agent-first code & file search engine. AST-aware chunking + BM25 + native MCP, 30MB zero-dep binary. Cuts AI token usage ~80% vs grep+Read. macOS/Windows/Linux.
Medical AI Assistant V0.2
AI ENGINEER PROJECTS
Memory Rag
Personal-memory RAG for an AI coding agent: BM25 + bge vectors + file-level RRF, CLI/MCP dual outlets, 18-query golden eval (18/18, MRR .880)
Inkdex
Semantic search for markdown docs
Grepnotes
Search your notes from Claude Code, Cursor, or any MCP client. Zero dependencies, runs fully offline.
Officeqa Arena
Sentient Arena Challenge 0: OfficeQA agent with BM25 search MCP server
Docwise
RAG-in-a-Box — intelligent document understanding for PDF, DOCX, and Markdown. Adaptive parsing, hybrid search (semantic + BM25), and agentic Q&A with citations. Upload, ask quest…
Langgraph Basketball Agent
AI-powered Basketball Assistant built to explore MCP, LangGraph, RAG, Hybrid Search, Text-to-SQL and modern AI Agent architectures using local LLMs.
Vacancy Radar
A local-first job application tracker. A markdown vault is the source of truth; a derived LanceDB index provides hybrid BM25 + vector search; an MCP server exposes read/write tool…
Codeguard Rag MCP
Evidence-grounded Python defect and vulnerability diagnosis with Hybrid RAG, MCP, ChromaDB, BM25, and RRF.
Finco
RAG over SEC EDGAR filings — hybrid BM25 + dense retrieval with rank fusion and cross-encoder reranking. +75% recall@5 over dense-only, with the eval harness that proves it.
Knowledge Service
Reusable MCP-based knowledge retrieval service with ingestion, Hybrid Retrieval, citations, and collection-based isolation.
Semantic Code Intelligence
Local-first semantic code search with FAISS, BM25, cross-encoder reranking, reliability scoring, and cited walkthroughs.
Lancedb Search MCP
MCP server for local-first document knowledge bases: LanceDB hybrid search (bge-m3 + CrossEncoder rerank), native BM25 with jieba, and PDF-to-LaTeX ingestion via a local MinerU pi…
Markdown Memory
MCP server that hands coding agents the one Markdown section that answers the question, not the whole file. Local hybrid search: BM25 keywords + ONNX embeddings in SQLite. No API…
AskMiao
🐱 Enterprise knowledge-base chat that cites its sources. Hybrid RAG (FAISS + BM25 + Cross-Encoder rerank) with an agentic research loop, custom API & MCP tools with user approval,…
Pagelore
Durable project memory for AI coding agents (Claude Code, Codex, Cursor, Gemini CLI): decisions and bug post-mortems as markdown pages in your repo, BM25F search via CLI or MCP se…