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.
-
Shared memory for AI agents, kept as notes in your Obsidian vault: an MCP server that lets Claude Code, Codex and other agents find each other's decisions via BM25 search.
MIT -
A self-contained MCP stdio server for coding agents: BM25 code search, an aider-style codemap, and embedded read/find/grep (ripgrep as a library).
cargo MIT -
docent-mcpgithub.com/cuzfrog/docent-mcpupdated this year
Semantic + BM25 Document search MCP server
MIT ★ 1 -
qexgithub.com/us/qexupdated this year
Lightweight MCP server for semantic code search — BM25 + optional dense vectors + tree-sitter chunking
AGPL-3.0 ★ 3 -
officeqa-arenagithub.com/Zhekinmaksim/officeqa-arenaupdated this year
Sentient Arena Challenge 0: OfficeQA agent with BM25 search MCP server
-
obsidian-vault-mcpupdated this year
MCP server for Obsidian vault with BM25 search, backlinks, tags, and more
npm MIT -
Read-only MCP server: hybrid (BM25 + embeddings) search over a folder of Markdown/text docs, built to treat the calling LLM as untrusted.
MIT -
oboyugithub.com/sonesuke/oboyuupdated this year
Self-hosted MCP Japanese text indexing & search—chunking+embeddings with BM25×vector rerank
pypi MIT ★ 3 -
Read-only MCP server for 1C BSL code search: hybrid BM25 + vector kNN retrieval over methods in Elasticsearch, RRF, dedup, rerank — context for code LLMs. | MCP-сервер поиска по коду 1С BSL: гибридный BM25 + векторный поиск по методам в Elasticsearch, RRF, дедупликация, ранжирование.
★ 3 -
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 -
Native tool search for DeepSeek Harness (DSH). Discover built-in, plugin and MCP tools on demand with BM25 or optional Ollama/OpenAI embeddings.
npm Apache-2.0 ★ 2 -
MCP server for agent memory backed by SQLite (WAL mode) with hybrid FTS5 BM25 + cosine vector search
npm GPL-3.0-or-later -
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.
★ 2 -
js-vector-store-headlessgithub.com/mauricioperera/js-vector-storeupdated this year
Headless semantic search API powered by js-vector-store and local Ollama embeddings. Vector + BM25 + Hybrid search with MCP and REST endpoints.
npm MIT -
High-performance Go-based Semantic Memory MCP Gateway for AnythingLLM with Hybrid Vector & FTS5 BM25 Search
MIT ★ 1 -
homebrew-amanmcpgithub.com/Aman-CERP/homebrew-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.
-
Local hybrid-search (BM25 + vector + reranking) MCP server — ask questions of any local codebase or document folder, fully offline
pypi MIT ★ 9 -
Velesgithub.com/julymetodiev/Velesupdated this year
Fast hybrid (BM25 + semantic) local code search for AI agents - pure Rust, persistent index, MCP/gRPC servers, tree-sitter symbols
cargo ★ 9 -
MCP server that BM25-searches any number of `llms.txt` documentation indexes(Strands, Kiro, AWS user/dev guides, and any you add at runtime), then fetches full doc content on demand.
npm MIT -
Local, private "where did I write that?" search for your notes, built for coding agents: BM25 + local Ollama embeddings, MCP server, disk-verified results.
MIT ★ 1 -
engramgithub.com/claudettetheai/engramupdated this year
Production-grade persistent memory for AI agents. Hybrid BM25 + vector search, knowledge graph, lifecycle hooks. 250K+ memories. Built by an AI, for AIs.
MIT -
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 pipeline
MIT -
Search for 1C (BSL code + configuration metadata) exposed to LLM agents via MCP: local e5/Chroma retrieval, global BM25 + RRF hybrid, optional cross-encoder, file-level eval (nDCG@10 / MRR).
MIT -
engramgithub.com/199-biotechnologies/engramupdated this year
MCP server for AI memory -- hybrid search (BM25 + semantic + knowledge graph), temporal decay, local-first
npm MIT ★ 10 -
Self-contained MCP server for hybrid document search (BM25 + dense RRF) — retrieval-only, works out of the box, Prometheus metrics, Docker, CI/CD
MIT -
codemeshgithub.com/gkatte/codemeshupdated this year
BM25 keyword search + graph walk for code intelligence. 100% local. No API keys. 9 languages. MCP server for AI coding agents.
MIT ★ 1 -
knowledge-mcp-servergithub.com/achellesheel/knowledge-mcp-serverupdated this year
Local MCP server + CLI turning PDFs/notes into a semantic knowledge base — FAISS + sentence-transformers, hybrid BM25/dense search, cross-encoder reranking, eval-driven.
MIT -
anydocsgithub.com/kiyeonjeon21/anydocsupdated this year
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.
MIT -
agent-context-codegithub.com/tlines2016/agent-context-codeupdated this year
A 100% local semantic code search tool featuring hybrid search (vector + BM25), AST-aware chunking, and native MCP integration for AI coding assistants.
MIT ★ 3 -
pixelbadger.toolkit.raggithub.com/pixelbadger/pixelbadger.toolkit.ragupdated this year
A CLI toolkit for RAG (Retrieval-Augmented Generation) workflows, providing BM25 search indexing, querying, semantic chunking, and MCP server functionality powered by Lucene.NET.
nuget MIT -
descrygithub.com/jKiler/descryupdated this year
Local hybrid (vector + BM25) code search for AI coding agents — AST chunking, MiniLM embeddings on ONNX, Go call graph, MCP server. No external services.
go Apache-2.0 ★ 1 -
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.
MIT -
sivrugithub.com/sivru/sivruupdated this year
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
npm MIT ★ 4 -
@adamrdrew/agent-memory-mcpgithub.com/adamrdrew/agent-memory-mcpupdated this year
MCP server for persistent agent memory — hybrid BM25 + vector search backed by LanceDB with local ONNX embeddings. No API keys, fully local.
npm GPL-3.0-or-later -
Local semantic code index — hybrid search (vectors + BM25), one warm embedding model, served over CLI, HTTP, a Rust client and an MCP bridge for coding agents.
★ 2 -
Local, unlimited web-search MCP server with BM25 ranking, Playwright crawling, and smart YouTube transcript extraction. DISCOVERY MODE: Get chapter outlines first, then extract specific sections. Perfect for long videos & bug fix workflows. No Docker, no
npm MIT -
Crawl, index, and hybrid-search documentation sites; served to LLM agents as an MCP server. FastAPI + DuckDB + BM25/embeddings, fully offline-testable.
MIT -
Local hybrid search for Korean Markdown notes & Obsidian vaults (BM25 + Hangul bigram + Qwen3 + rerank, MCP/CLI/SDK) · 한국어 마크다운 로컬 검색
npm MIT -
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 -
llmdocgithub.com/bigbag/llmdocupdated this year
MCP documentation server with BM25 search, multi-source support, and llms.txt integration
pypi MIT -
claude-remind-mcpgithub.com/emretheus/claude-remind-mcpupdated this year
MCP server for searching past Claude Code conversation history. Local BM25 search over JSONL logs with persistent index, secret redaction, solved-hint, and instant claude --resume.
npm MIT ★ 1 -
needlegithub.com/alexandremourin/needleupdated this year
Semantic code search MCP server: tree-sitter chunking + local Model2Vec embeddings + BM25/dense hybrid (RRF). Hands an AI only the relevant code (file:line), ~10-100x fewer tokens. Multi-language, no API key.
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 -
aikdgithub.com/gelutjari/aikdupdated this year
Indexed semantic & BM25 code search for AI agents. Give your AI instant memory of your codebase. Rust | MCP Server.
★ 2 -
Turn a folder of ebooks into a searchable, citable knowledge base: hybrid BM25 + vector search, grounded Q&A with citations, and an MCP server, all in one DuckDB file.
MIT -
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 tools to any LLM client.
pypi MIT -
Persistent multi-path memory for AI agents — vector + BM25 keyword + entity graph search with RRF fusion, credential scrubbing, auto-consolidation, multi-backend storage (Qdrant + SQLite/Postgres)
npm MIT -
kxgithub.com/distu/kxactive
Local-first MCP server and CLI for AI coding agents. Hybrid semantic + BM25 search across code, docs and notes, with SQLite and offline embeddings.
MIT ★ 5 -
CogniVaultgithub.com/gitstq/CogniVaultupdated this year
🧠 CogniVault - Lightweight AI Agent Semantic Memory Engine | 轻量级AI Agent语义记忆引擎 - Zero Dependencies, TF-IDF+BM25 Hybrid Search, Memory Lifecycle, Knowledge Graph, MCP Server
MIT -
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 -
amemgithub.com/alejandroSuch/amemupdated this year
Agentic Memory MCP server — BM25 search, inter-memory links, and enriched metadata for AI coding agents
-
多模态内容理解与工具编排 Agent:Chinese-CLIP 图文共享向量空间 + BM25/RRF 混合检索 + cross-encoder 重排(真实文本查询 hit@10 0.668→0.918)+ Schema 约束工具调用 + 可溯源生成,含 MCP、多轮会话记忆、ReAct 编排与分层离线评测。 | Multimodal agent: Chinese-CLIP retrieval, BM25+RRF hybrid search, cross-encoder reranking, schema-constrained tool calling, MCP server.
MIT -
Local code search combining BM25, vector similarity, and cross-encoder reranking. Parses 60+ languages with tree-sitter, runs entirely offline, and returns structured results with file paths, line ranges, and symbol metadata. Built in Rust.
pypi MIT ★ 150 -
melchizedekgithub.com/louis49/melchizedekupdated this year
Persistent memory for Claude Code. Automatically indexes every conversation and provides production-grade hybrid search (BM25 + vectors + reranker) via MCP tools. 100% local, zero config, zero API keys.
npm MIT ★ 8 -
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 keys, no network.
MIT ★ 1 -
Local RAG MCP server for sing-box docs using hybrid search (FAISS + BM25) and Reciprocal Rank Fusion.
MIT ★ 7 -
embedbasegithub.com/jaymeklein/embedbaseupdated this year
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 pluggable parsers, embedders, and vector stores.
★ 1 -
Multi-repo semantic code search MCP server in Rust — hybrid vector + BM25 retrieval, tree-sitter AST chunking, fully offline. For OpenCode, Claude Code, Cursor, and any MCP client.
Apache-2.0 ★ 104 -
🚀 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 support (Windows/Linux/macOS).
MIT -
mcp-docs-servergithub.com/praveenc/mcp-docs-serverupdated this year
MCP server for searching Model Context Protocol documentation. BM25 search, auto-indexing, TypeScript. Works with Cursor, WindSurf, Claude Desktop, Kiro, and any MCP client.
npm ★ 2