- 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.
S1grep
Semantic code search that runs on your machine: describe what the code does, in English or Spanish, and get the exact function. Local embeddings + BM25 + s1-code, our own small ju…
Engmem
Personal engineering memory for AI-assisted development: a local Markdown store your coding agent searches before it plans
Hybrid Rag
MCP server exposing hybrid RAG (BM25 + dense + RRF + reranking) over SEC filings — with FastAPI backend, Next.js frontend, and 22-query evaluation.
Hippocampus
Self-hosted persistent long-term memory for Claude Code and MCP clients. One memory for every session and machine: hybrid BM25 + local vector + knowledge-graph search over plain M…
Zerograph
Knowledge graph of a repository's docs and code (15+ languages): ask by id, keyword or paraphrase, trace impact, serve it to agents over MCP — built and refreshed at zero model to…
Docs MCP Server
Multi-tenant MCP server for documentation search and retrieval.
RAG Codebase
Code-aware RAG over a repository: AST-boundary chunking (tree-sitter), hybrid dense+BM25 retrieval with RRF & reranking, a code graph (imports/calls + PageRank), grounded citation…
Mosaic
Local, deterministic semantic search built from textbook parts - measured, defeats included. A didactic experiment that runs in production.
Knowshelf
Personal Markdown Book Knowledge Base MCP Service. 个人 Markdown 书籍知识库 MCP 服务。
Tool Search Oss
BM25 tool search for MCP — find the right tool from 50+ without context collapse. Works with any LLM.
Anythingllm MCP Gateway
High-performance Go-based Semantic Memory MCP Gateway for AnythingLLM with Hybrid Vector & FTS5 BM25 Search
Claudebase
Local infrastructure for LLM agents — hybrid retrieval, cognitive memory, persistent channels
Layout Aware RAG
Layout-aware RAG over engineering datasheets: hybrid dense/BM25 retrieval at page-native layout-region granularity, with region-level evidence provenance
Biomedical Rag Research Assistant
Biomedical RAG assistant for PubMed documents featuring hybrid ChromaDB and BM25 retrieval, MiniLM embeddings, RRF, grounded citations, guardrails, MCP tools, FastAPI, Streamlit,…
Obsidian Chromadb Self Evolving Kb
面向 Markdown 知识库的自进化 RAG 检索引擎：BGE 向量 + BM25 + RRF 融合检索，两阶段 Rerank，反馈驱动 BGE 微调闭环（离线闸门保障安全上线）。开箱自证检索质量，支持 Obsidian 同步与 FastAPI/MCP 服务。
AI Workstation
Model-agnostic local AI workstation and offline hybrid RAG knowledge system
Flux7 Memory
Governed multi-agent memory for AI agents — hybrid markdown+SQLite, FTS, vector search, LLM reranking. One Go binary, MCP stdio + HTTP + SSE.
Dsh Geometry Knowledge
几何论（共扼谱几何 CSG）知识库插件 for DeepSeek Harness：纯离线 BM25 检索 251 篇文章 + 869 条真理，31 个 geo_* 工具，开箱即用。Conjugate Spectral Geometry knowledge base plugin for DSH.
Vbrain
A private, AI-queryable second brain — as a reusable engine: BM25 search, a knowledge graph, an MCP server for AI agents, quick-capture, and an SEO static-site export. Ships with…
Embedbase
Local-first document embedding and retrieval platform with a REST API and MCP server for LLM agents. Supports hybrid BM25 + semantic search across workspaces and collections, with…
Aidememo
Local-first memory for coding agents: typed facts, knowledge graphs, temporal history, MCP, SDKs, and CLI in one Rust binary.
BlooRecall
Local, private "where did I write that?" search for your notes, built for coding agents: BM25 + local Ollama embeddings, MCP server, disk-verified results.
Misakanet Core
Zero-dependency BM25 + RRF search engine for failure lessons. pip install misakanet-core
Knowify
Agentic RAG chatbot with hybrid retrieval (BM25 + dense), cross-encoder reranking, and a self-correcting retry loop. Long-term memory, MCP client/server support, and RAGAS-evaluat…
Opencode Memory
Distributed local-first hybrid-RAG memory layer and Harness bootstrapper for opencode agents, with dynamic pre-injection and styled console TUI.
One Mind
Shared memory layer for AI agents — SQLite + threaded HTTP daemon + MCP server. BM25 retrieval, provenance tracking (agent_id), garbage collection. Pluggable architecture, 40+ tes…
CortexDB
High-performance persistent memory and knowledge engine for AI coding assistants via Model Context Protocol (MCP).
Ripsem
Local, offline semantic code search with an MCP server for coding agents
Qex
Lightweight MCP server for semantic code search — BM25 + optional dense vectors + tree-sitter chunking
Claude Persistent Memory
Give Claude Code persistent memory across sessions. Hybrid BM25 + vector semantic search, auto-structuring via LLM, and 4-channel retrieval (MCP + hooks). Your AI assistant finall…
RAG In A Box
RAG pipeline for documents (Markdown, PDF, images). 10-step hybrid search, LLM enrichment, taxonomy, MCP server. Cloud or local.
Ferrex
Persistent memory for AI agents. Stores facts, events, and procedures with intelligent retrieval, entity resolution, and staleness scoring. Fully local.
Vectorize MCP Worker
Hybrid RAG Worker on Cloudflare Edge — Vector + BM25 search, metadata filtering, multimodal vision, MCP server, and intelligent query routing. ~400ms p99.
Automatised Pipeline
Codebase intelligence as an MCP server — tree-sitter AST → LadybugDB graph → Louvain communities → hybrid BM25 + TF-IDF + RRF search. 23 tools · 10 stages · 220 tests · Rust · Cle…
Graphstore
Memory infrastructure for AI agents!! store, recall by meaning or association, ingest documents, and track beliefs in one Python library.
Docent MCP
Semantic + BM25 Document + Git history search MCP server
Veles
Fast hybrid (BM25 + semantic) local code search for AI agents - pure Rust, persistent index, MCP/gRPC servers, tree-sitter symbols
Ostk Recall
Local-first cross-corpus retrieval MCP server — model2vec embeddings + LanceDB (Tantivy BM25) + SQLite. One binary; hybrid (dense + BM25) search across markdown, code, and Claude…
Aikd
Indexed semantic & BM25 code search for AI agents. Give your AI instant memory of your codebase. Rust | MCP Server.
Rag Ferrite
Personal RAG engine — simple, fast, Rust. One binary (15 MB), one DB, native collections. MCP-native.
Sivru
Code search and session observability for coding agents. Hybrid BM25+semantic, optional cross-encoder rerank, self-bench on your own data. npm install -g @sivru/cli
Bdh Graph Harness
Graph-based retrieval for Obsidian vaults with Hebbian synaptic plasticity
Langhuan
把知识库变成可被 MCP 调用的检索服务 —— 单二进制、中文友好的 RAG 知识处理层 Turn your knowledge base into an MCP-callable retrieval service — a single-binary, Chinese-friendly knowledge processing layer for RA…
Ohmyrepos
Oh My Repos: Semantic search for GitHub starred repositories.
Biblium
Your AI's personal library — MCP knowledge base server (Go, EUPL-1.2)
Agent Session Mirror
Best AI Coding Agent Observability Tool 2026 - Self-Bench & Semantic Search
BM 25 Search
MCP server and CLI for BM25 keyword search over a local Markdown corpus — drop .md files into data/ and query from any MCP-compatible client or the command line.
Descry
Local hybrid (vector + BM25) code search for AI coding agents — AST chunking, MiniLM embeddings on ONNX, Go call graph, MCP server. No external services.
Repository Mind
A desktop tool that turns GitHub repositories into evidence-based project reports and AI-readable indexes.
Shelfmark
Local hybrid retrieval (BM25 + embeddings) for agent memory & code, in one SQLite file. No cloud, no services. MCP server included for Claude Code and other agents.