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.
-
lancedb-mcp-servergithub.com/gongxh13/lancedb-mcp-serverupdated this year
MCP server for LanceDB
npm ISC -
—
★ 7 -
—
★ 9 -
—
★ 27 -
LanceDB MCP Server nodejs
-
lancedb-mcphttps://gitlab.com/skopciewski/lancedb-mcpupdated this year
MCP server providing semantic knowledge base with LanceDB storage and configurable embeddings
pypi GPL-3.0-or-later -
cocoindex-hnsw-lancedbgithub.com/systemgroupnet/cocoindex-hnsw-lancedbupdated this year
Cocoindex-based code indexing service with HNSW, automatic disk compaction, MCP Server, periodic git pull, metrics push to MySQL, and space-efficient branch searching
Apache-2.0 ★ 8 -
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 -
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 -
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 -
rmcp-memexgithub.com/vetcoders/rmcp-memexupdated this year
RAG/memory MCP server with LanceDB vector storage
cargo MIT OR Apache-2.0 -
ramemgithub.com/planetf1/ramemupdated this year
Local, offline AI agent memory using LanceDB and MCP — the ram CLI
cargo Apache-2.0 -
CAIgithub.com/piot5/CAIupdated this year
Modular framework with vector database (LanceDB), filesystem archive (Mycelium), MCP server ecosystem, and Blender simulation
MIT ★ 3 -
codebasesearchgithub.com/anentrypoint/codebasesearchupdated this year
Ultra-simple code search tool with Jina embeddings, LanceDB, and MCP protocol support
npm -
Local-first Ollama + LanceDB code index for MCP agents — retrieve snippets instead of re-scanning the repo.
npm MIT -
MCP server for semantic search over an Obsidian vault using LanceDB and OpenAI/Ollama embeddings
MIT ★ 2 -
OpenClawdCodegithub.com/TechFath3r/OpenClawdCodeupdated this year
Persistent memory + context engine for Claude Code via MCP. Spiritual port of OpenClaw memory-lancedb-pro and lossless-claw to Claude Code. Local-only (LanceDB + Ollama + Obsidian).
MIT -
@dolusoft/hirebase-mcpgithub.com/dolusoft/hirebaseupdated this year
HireBase - AI-powered CV search engine with LanceDB and MCP
npm MIT -
FastMCP PDF intelligence: extract, manipulate, annotate, convert, validate, and LanceDB RAG — with a React PDF.js workbench.
MIT ★ 1 -
glanceygithub.com/nicholaspsmith/glanceyupdated this year
MCP plugin for semantic code search using LanceDB - gives AI coding agents deep context from your entire codebase
npm MIT -
Week-stamped, incremental index of Claude Code session transcripts: embedded PocketBase + LanceDB replica, Rust watcher, macOS tray, HAOS add-on, MCP with OAuth
MIT -
@indokq/memory-mcpgithub.com/indokq/memory-mcpupdated this year
MCP server for semantic memory and codebase search with LanceDB and Voyage AI embeddings
npm MIT -
lance-contextgithub.com/nicholaspsmith/lance-contextupdated this year
MCP plugin for semantic code search using LanceDB - gives AI coding agents deep context from your entire codebase
npm MIT -
Teachable RAG pipeline on OneBucket: chunking, hybrid embeddings, LanceDB and an MCP search server
MIT -
Persistent, project-scoped memory for AI agents. Local-first (LanceDB + Ollama), five MCP tools, admin web panel and Claude Code hooks.
Apache-2.0 -
API service to search vectorized Cursor IDE chat history using LanceDB and Ollama
★ 4 -
MCP-сервер для поиска UI-компонентов с использованием RAG на базе LanceDB и GigaChat
npm MIT -
agent-memory-hubgithub.com/NanAnNuo/agent-memory-hubupdated this year
Local-first memory hub for Codex, Claude, and OpenCode with SQLite, LanceDB, isolated skills, MCP tools, and a Windows dashboard.
MIT ★ 4 -
@david03xu/agentcoregithub.com/david3xu/agentcoreupdated this year
Local-first AI memory engine for multi-agent workflows — 17-tool MCP server. Zero config (LanceDB) or Azure (Cosmos + AI Search).
npm MIT -
Cursor-history-MCPgithub.com/Nossim/Cursor-history-MCPupdated this year
API service to search vectorized Cursor IDE chat history using LanceDB and Ollama
★ 7 -
Persistent memory system for Claude Code via MCP — dual-write to Markdown + LanceDB with hybrid semantic search
npm MIT -
@iflow-mcp/adshaa-mempalacejsgithub.com/iflow-mcp/adshaa-mempalacejsupdated this year
Native TypeScript AI memory system and MCP server (Zero-LLM, LanceDB)
npm ISC -
Local MCP repository search in Go with Tree-sitter AST chunks, LanceDB vectors, and a reproducible CPU-only token-hashing baseline.
MIT -
knowledge-mcpgithub.com/ikuzuki/knowledge-mcpupdated this year
Hybrid BM25 + vector MCP retrieval over a markdown vault (SQLite FTS5, LanceDB, Ollama). Later retired in favour of plain grep; the write-up explains why.
MIT -
rag-mcp-servergithub.com/ElnurIbrahimov/rag-mcp-serverupdated this year
RAG MCP server for Claude Code — hybrid search (vector + BM25), code-aware chunking, PDF support. Uses Ollama nomic-embed-text + LanceDB. Fully local, zero API costs.
MIT -
Memory layer MCP for AI coding agents — durable save/recall/update on Gemma embeddings + embedded LanceDB hybrid retrieval
npm MIT ★ 5 -
Local RAG semantic search for Obsidian vaults — Ollama + LanceDB + MCP. Search your markdown vault by meaning, not keyword.
MIT ★ 5 -
Local-first Hybrid GraphRAG engine + MCP server for Obsidian vaults — LadybugDB graph + LanceDB vector/BM25 with RRF, no Docker, no cloud.
MIT ★ 1 -
@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 -
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 -
Self-hosted personal memory & RAG system — LanceDB vault, MCP query API, and a daemon fleet (curator, distiller, surveyor, consolidator, janitor) that ingest, classify, and maintain a knowledge graph ambiently.
-
codebase-rag-mcpgithub.com/Chri2K02/codebase-rag-mcpupdated this year
MCP server for semantic code search and Q&A — indexes any codebase using vector embeddings (OpenAI + LanceDB), exposes 4 tools to Claude Desktop, Cursor, and Copilot Chat
-
Persistent, local, cross-IDE memory for AI agents — markdown source of truth, LanceDB-powered semantic search, zero cloud dependency
cargo MIT ★ 66 -
Local-first AI knowledge base desktop app: PDF/DOCX/image ingestion, OCR, chunking, embedding, LanceDB vector search, MCP access, and optional AnythingLLM sync. Windows EXE packed.
-
MCP Server for vector-based semantic code search in Claude Code. Index your codebase locally with LanceDB and search code, files, and symbols using natural language.
npm MIT -
Local-first MCP server for RAG over engineering documentation (GOST/SP, project PDF/DOCX/XLSX, IFC/DWG). Lemonade embeddings + LanceDB hybrid search with query planning and retrieval-quality filtering.
MIT -
Blueprint for spinning up read-only SQL data agents from any SQLAlchemy-compatible database. Indexes schema and column content into LanceDB and exposes MCP + REST tools so LLMs and UIs can safely explore your data.
Apache-2.0 ★ 4 -
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 -
bookmark-lensgithub.com/cornelcroi/bookmark-lensupdated this year
Local-first bookmark manager with semantic search for MCP-enabled AI assistants. AI-powered organization, smart tagging, and natural language queries. Built on LanceDB. Works with Claude Desktop, Cursor, and other MCP clients.
MIT ★ 6 -
Self-hosted, source-cited RAG for OpenCode and AI coding agents. LanceDB + MiniLM hybrid retrieval, MCP server, verbatim cited answers with abstention, OmniRoute routing. CPU-only.
MIT -
Serveurs MCP de recherche sémantique pour Claude : débats de l'Assemblée nationale et synopsis de films. bge-m3 + LanceDB, en local, sans clé API.
MIT -
preflightgithub.com/preflight-dev/preflightupdated this year
✈️ 24-tool MCP server for Claude Code: preflight checks for your prompts, cross-service context, session history search with LanceDB vectors, correction pattern learning, cost estimation
MIT ★ 13 -
ai-longterm-wiki-memory-ClaudeCodegithub.com/giovannifrontera/ai-longterm-wiki-memory-ClaudeCodeupdated this year
Persistent semantic memory for Claude Code. Three-layer wiki + LanceDB vectors, hooks, self-healing lint, knowledge graph. Native MCP integration.
AGPL-3.0 ★ 1 -
로컬 하이브리드 코드·PDF 검색 서버 — 레거시 여러 벌 + 현재 코드 + 사양서를 인덱싱해 AI 코딩 에이전트에 파일·심볼·줄 범위로 답한다 (LanceDB · Ollama bge-m3 · Roslyn/PdfPig · MCP/Claude Code/Codex)
MIT -
UltraMemorygithub.com/win4r/UltraMemoryupdated this year
Universal AI Agent Long-Term Memory Engine — Hybrid Vector+BM25, cross-encoder reranking, Weibull decay, LLM smart extraction, semantic dedup, tiered content. Zero-ops LanceDB backend.
★ 7 -
Local-first MCP server in Python for hybrid search (vector + full-text, reranking, graph navigation) across Obsidian vaults and Markdown knowledge bases. Built on LanceDB.
MIT ★ 1 -
Agentic RAG for local and self-hosted document search: hybrid retrieval, reranking and multimodal RAG on embedded LanceDB, with Docling parsing and an MCP server
pypi MIT ★ 660 -
context-lensgithub.com/cornelcroi/context-lensupdated this year
Semantic search knowledge base for MCP-enabled AI assistants. Index local files or GitHub repos, query with natural language. Built on LanceDB vector storage. Works with Claude Desktop, Cursor, and other MCP clients.
pypi MIT ★ 24 -
Local semantic + keyword search across your Obsidian vault and source repos. LanceDB + Ollama (bge-m3), exposed to Claude Code and Cowork over MCP. Privacy-first: no cloud, no API keys, no telemetry.
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