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.
-
@saluca/asphodelgithub.com/salucallc/asphodelupdated this year
Local-first agent memory — topic index, FTS, hybrid vector search (BM25 + embeddings + RRF), temporal decay, importance/ttl/persona scoping, bundled MCP server
npm Apache-2.0 -
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 -
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 -
Self-hosted web search MCP server (Node). 6 engines (CN-direct + Intl-via-proxy auto-routing), RRF fusion, SimHash dedup, per-host rate limiting, frequency-aware cache, TLS/JA3 impersonation fallback. Tools: web_search / fetch_url / deep_research.
MIT -
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 -
Unified multi-provider search & content-extraction MCP server & aggregates Exa/Serper/Tavily/Firecrawl/Jina with RRF fusion
MIT -
A context database for LLMs: structured storage and hybrid retrieval (BM25 + vectors, RRF-fused, token-budgeted) over SQLite, exposed to Claude as an MCP server
MIT -
seeklinkgithub.com/simonsysun/seeklinkupdated this year
Local semantic search CLI and optional MCP stdio server for Markdown vaults. BM25 + vector + wikilink graph + metadata via RRF. Native CJK.
pypi MIT -
fieldcure-mcp-raggithub.com/fieldcure/fieldcure-mcp-ragupdated this year
RAG MCP server with SQLite FTS5 trigram + vector hybrid search (RRF). Features IChunkContextualizer for AI-powered bilingual keyword generation and cross-lingual document search.
MIT -
RAG proof of concept: hybrid retrieval (pgvector HNSW + lexical RRF), cross-encoder reranking, dual embeddings (OpenAI + local GPU/CPU), and an MCP server — Python, PostgreSQL, Docker (NVIDIA/ROCm)
-
High-performance Technical Knowledge Base & MCP Server powered by PostgreSQL 17, pgvector (HNSW), Lexical Search (GIN), Reciprocal Rank Fusion (RRF), and Automated Technical Entity Graph Extraction.
MIT ★ 2 -
Persistent long-term memory for Claude Code agents — SQLite + FTS5 + sqlite-vec + RRF hybrid recall over MCP, with Chinese tokenization. Local-first, graceful degradation.
MIT ★ 8 -
Semantic code search MCP server: Tree-sitter AST chunking + voyage-code-3 embeddings + hybrid retrieval (sqlite-vec + FTS5 + RRF) + Voyage rerank-2.5 + call graph expansion
MIT ★ 2 -
MCP server exposing hybrid RAG (BM25 + dense + RRF + reranking) over SEC filings — with FastAPI backend, Next.js frontend, and 22-query evaluation.
MIT ★ 2 -
gomaagithub.com/M4F-S/gomaaactive
Gomaa — Autonomous Agent Memory OS. Persistent memory system for AI agents with Obsidian vault integration, hybrid RRF search, knowledge graphs, security gates, and MCP server.
Apache-2.0 ★ 34 -
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
Apache-2.0 ★ 5 -
semcode-mcpgithub.com/huawang1258/semantic-code-mcpupdated this year
Semantic code search MCP server: Tree-sitter AST chunking + voyage-code-3 embeddings + hybrid retrieval (sqlite-vec + FTS5 + RRF) + Voyage rerank-2.5 + call graph expansion. Thin npx wrapper that launches the Python package via uvx.
npm MIT -
Federated, local-first search for an AI — one query across transcripts, files, knowledge graph, vector store, and the web, fused by trust-weighted RRF. Apache-2.0.
Apache-2.0 ★ 28 -
Persistent memory MCP server (MemoryIndustry) — self-growing knowledge graph that works without MCP sampling, poisoning quarantine, PostgreSQL + pgvector, bitemporal facts, BM25+RRF hybrid search, graph metrics/communities, Hebbian learning, episodic memo
npm Apache-2.0 -
Global, governed, bitemporal memory engine for autonomous AI coding agents & IDEs — shared ~/.memcore brain across Claude Code, Cursor, Antigravity, Codex, Gemini & Hermes with SQLite WAL + FTS5 BM25 + RRF hybrid recall over stdio MCP.
MIT ★ 1 -
Filesystem-first hybrid vector memory engine & MCP server in Go. Couples human notes (Obsidian/Copyparty) with PostgreSQL + pgvector, hybrid RRF search, graveyard safety guardrails, and parent-child chunking for nomic-embed-text-v2-moe.
-
Self-hosted AI knowledge base with hybrid semantic search (pgvector + FTS + RRF), MCP server, multi-provider LLM inference (Ollama, OpenAI, OpenRouter, llama.cpp), multimodal ingestion (vision, audio transcription, speaker diarization), and knowledge graph. Rust + PostgreSQL.
NOASSERTION ★ 30 -
AI Memory & Knowledge Management MCP Server — 32 tools, BM25 R@5=95%, hybrid search (RRF), knowledge graph, analytics, cloud sync, Obsidian compatible. Works with Claude Code, Cursor, Gemini CLI, Windsurf, hermes-agent.
npm MIT -
Local-first hybrid semantic code search tool. Indexes codebases into PostgreSQL with pgvector embeddings via Ollama, combines vector similarity + keyword search with RRF fusion. Supports 30+ languages. Features CLI, MCP server, WEB dashboard and interactive REPL.
MIT ★ 37 -
Persistent local memory for Claude, Cursor & Codex. 21 MCP tools, hybrid retrieval (BM25 + vector RRF), bi-temporal queries, contradiction detection. SQLite + Knowledge Graph. No cloud, no API keys. npx @studiomeyer/local-memory-mcp
npm MIT ★ 16 -
Local MCP server for semantic code search. AST-aware chunking with tree-sitter, offline ONNX embeddings, hybrid vector + BM25 (RRF) ranking, one SQLite file. No API keys or cloud. Semantic code search for Claude Code, Cursor, opencode and AI coding agents.
MIT -
100% Free Developer Tier (zero API keys, zero wallet required): 15 deterministic AI agent & developer tools: AST context skeleton pruner, BPE token budget planner, BM25+RRF+MMR hybrid reranker, self-healing fuzzy diff patcher, polyglot AST symbol & comple
npm MIT -
@oomkapwn/enquire-mcpgithub.com/oomkapwn/enquire-mcpupdated this year
MCP server giving AI agents (Claude Code, Claude Desktop, Cursor, ChatGPT, Codex, OpenClaw) persistent long-term memory backed by your local Obsidian markdown vault. Hybrid retrieval (BM25 + ML embeddings + BGE reranker, RRF-fused), HNSW + int8 quantizati
npm MIT -
MCP server giving AI agents (Claude Code, Claude Desktop, Cursor, ChatGPT, Codex, OpenClaw) persistent long-term memory backed by your local Obsidian markdown vault. Hybrid retrieval (BM25 + ML embeddings + BGE reranker, RRF-fused), HNSW + int8 quantizati
npm MIT -
diogenes-context-code-solver-mcpgithub.com/stand-out-of-my-sun/diogenes-context-code-solver-mcpactive
100% Free Developer Tier (zero API keys, zero wallet required): 15 deterministic AI agent & developer tools: AST context skeleton pruner, BPE token budget planner, BM25+RRF+MMR hybrid reranker, self-healing fuzzy diff patcher, polyglot AST symbol & complexity analyzer, Tarjan circular dependency detector, stack-trace root-cause isolator,
MIT ★ 1 -
mcp-rag-agentgithub.com/luisrodriguesphd/mcp-rag-agentupdated this year
This repository presents a production-ready RAG system combining LangGraph agent with Model Context Protocol (MCP) integration. Features hybrid search using Reciprocal Rank Fusion (RRF) via MongoDB vector and text searches, grounded responses using COSTAR prompting, and automated RAGAS-based evaluation for building reliable, context-aware AI agents
★ 4 -
MCP server for mneme: 10 tools for vault-native memory in Claude Code and MCP-compatible clients.
npm Apache-2.0 -
knowshelfgithub.com/hi-horan/knowshelfupdated this year
Personal Markdown Book Knowledge Base MCP Service. 个人 Markdown 书籍知识库 MCP 服务。
Apache-2.0 ★ 1 -
High-performance Go-based Semantic Memory MCP Gateway for AnythingLLM with Hybrid Vector & FTS5 BM25 Search
MIT ★ 1 -
Vertical-domain information-specialist agent CLI : search + research + memory + knowledge with domain allowlists, abstain-first answers, and a fail-open MCP server
npm Apache-2.0 -
编码 agent 查资料缺搜索 API key?免 key 搜多个引擎、优先可靠来源并抽取可读正文。 Search the web and read pages without an API key.
MIT ★ 1 -
Find the RAG retrieval setup that works on your data, then use it automatically. HyDE, Step-Back, Fan-Out, hybrid BM25 search and reranking, benchmarked on your documents (Markdown, HTML, PDF, DOCX) and routed per query, with citations and streaming, for
npm MIT -
Persistent memory for AI coding agents. Local-first. MCP-native. Auto-captured from Claude Code, shared with Cursor, Codex, and any MCP client. Your agents don't remember what you decided yesterday. Sigil does. Every prompt, every session, your context is already there.
MIT ★ 10