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.
-
—
★ 47 -
RAG + context management MCP server: persistent memory, vector search, zero APIs
npm MIT -
claude-rag-memorygithub.com/jonburchel/claude-rag-memoryupdated this year
Personal semantic memory MCP server for AI assistants (Qdrant + OpenAI embeddings)
★ 1 -
RAG + Context Management MCP server: long-term memory, vector storage, knowledge retrieval. Run with npx, zero external APIs.
npm MIT -
A Model Context Protocol (MCP) server implementation for graph-based memory storage with RAG capabilities
-
rag-memory-pg-mcpgithub.com/kshidenko/rag-memory-pg-mcpupdated this year
PostgreSQL-based RAG Memory MCP Server with Supabase - knowledge graph + semantic search
npm MIT -
rag-memory-pg-mcpgithub.com/kshidenko/rag-memory-pg-mcpupdated this year
PostgreSQL-based RAG Memory MCP Server with Supabase - hybrid semantic search + knowledge graph
npm -
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)
★ 2 -
Project-local RAG memory MCP server — knowledge graph + multilingual vector + FTS5 in a single SQLite file. Per-project isolation, 30 MCP tools, codepoint-safe chunking (Korean/CJK/emoji).
npm MIT -
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
pypi Apache-2.0 ★ 5 -
A lightweight MCP server for RAG-based memory context management with local vector store
npm MIT -
running-coach-memory-mcpgithub.com/barcia/running-coach-memory-mcpupdated this year
Running Coach Memory MCP and RAG to save and get plans and insights from athletes
GPL-3.0 ★ 1 -
A RAG-based personal memory MCP server demo (FastMCP + ChromaDB)
★ 1 -
Local-first RAG knowledge base & agent memory service: hybrid retrieval + memory governance, REST + MCP, fully usable offline without an LLM
pypi Apache-2.0 -
local-memory-mcpgithub.com/ptobey/local-memory-mcpupdated this year
Persistent local memory for Claude and ChatGPT. No cloud, no subscription. Self-hosted RAG over MCP.
MIT ★ 10 -
Sovereign SQLite Vector Memory & Hybrid RAG Engine with Model Context Protocol (MCP) for AI Agents
MIT -
fusionpactgithub.com/fusionpacttech/fusionpact-vectordbupdated this year
The Agent-Native Retrieval Engine — Hybrid Vector + Reasoning + Memory for AI Agents. HNSW indexing, tree-based reasoning retrieval, built-in RAG, MCP server, multi-agent orchestration, and agent memory architecture.
npm Apache-2.0 -
opencode-memorygithub.com/xpajonx/opencode-memoryupdated this year
Distributed local-first hybrid-RAG memory layer and Harness bootstrapper for opencode agents, with dynamic pre-injection and styled console TUI.
★ 1 -
Production-grade, zero-dependency local Model Context Protocol (MCP) server providing cross-conversation memory and sub-2ms BM25 RAG for Antigravity workspaces.
pypi MIT -
Local-first memory, hybrid RAG, and agent personalization for AI coding agents. MCP + CLI for OpenCode, Codex, Claude Code, Gemini CLI, and Antigravity.
npm MIT ★ 2 -
fusionpact-vectordbgithub.com/FusionpactTech/fusionpact-vectordbupdated this year
⚡ The Agent-Native Retrieval Engine — Hybrid Vector + Reasoning + Memory for AI Agents. HNSW indexing, tree-based reasoning retrieval, multi-agent orchestration, MCP server, and built-in RAG.
npm Apache-2.0 -
Description: RAG memory + Claude MCP integration for Anantata project
-
Memory-enhanced MCP server with local RAG database and expiring memory capabilities
★ 3 -
App-first AI framework with a built-in, governed memory engine (memory, agents, RAG, MCP)
MIT ★ 4 -
pmem-project-memory-tool-for-claude-codegithub.com/avanrossum/pmem-project-memory-tool-for-claude-codeupdated this year
Local-first RAG memory for Claude Code. Semantic search over your project's docs, decisions, and history. No external APIs. Setup in 2 minutes.
MIT ★ 2 -
hyphaegithub.com/basidiocarp/hyphaeupdated this year
Persistent memory and RAG for AI coding agents. Episodic memories with decay + durable concept graphs. MCP server + CLI. Rust.
MIT ★ 2 -
Agent memory for Claude Code, Cursor, Codex: MCP server + Graph RAG over your Obsidian or markdown notes, a search layer for a Karpathy-style LLM Wiki. Wikilinks are the graph, SQLite the only store.
pypi MIT ★ 15 -
Voice + chat assistant with long-term memory built from scratch: LLM fact extraction, pgvector, conflict resolution (90% held-out accuracy vs 0% baseline), relevance-filtered RAG, a memory-poisoning screen, and Langfuse tracing. LangGraph, FastAPI, React/TS, MCP
-
Personal memory engine + MCP server — hybrid RAG (SQLite FTS5 + vector embeddings) over a git-backed markdown store
MIT ★ 3 -
surreal-mem-mcpgithub.com/tymorton/surreal-mem-mcpupdated this year
A standalone Edge-RAG Memory Daemon for autonomous AI agents. High-performance Rust core (SurrealDB/RocksDB + Axum) with Bayesian Math Retrieval, multi-language AST indexing, and enterprise Semantic Redaction.
MIT ★ 6 -
☀️ Persistent Memory + RAG + Wiki Compilation for AI Agents — MCP server + Web UI with interactive knowledge graph
MIT ★ 1 -
Simple RAG implementation from scratch using MCP, focusing on Perception, Memory, Decision and Action
Apache-2.0 ★ 15 -
MCP server for HotKV: lets AI agents read and write keys, agent memory, prompts and RAG documents.
Apache-2.0 -
M4-MCP-Agentgithub.com/carrey-Jin/M4-MCP-Agentupdated this year
A local-first, context-aware MCP server that gives Cursor persistent memory + private RAG, powered by Ollama.
MIT -
Mnema — one memory for every AI agent. Shared memory, RAG and project maps over MCP + REST; SQLite hybrid search, multi-device sync, self-hosted.
MIT ★ 3 -
Persistent memory for AI agents over MCP: knowledge graph, vectors and graph RAG on your own hardware. Install a node, connect Claude Code or another agent, use the seven memory tools.
pypi Apache-2.0 ★ 1 -
Rust RAG engine — Tree-sitter parsing, Tantivy search indexing, vector memory with cosine similarity — 22 MCP tools.
MIT -
Self-hosted long-term memory for AI coding agents: Postgres+pgvector doc-RAG (component/constraint map + hybrid RRF + cross-encoder rerank) and bi-temporal personal memory. MCP-native, local-model friendly.
MIT ★ 17 -
Code_MCP_Toolsgithub.com/warc0s/Code_MCP_Toolsupdated this year
Local-first MCP server and web panel for agent memory, project docs, bugs, todos, and RAG search
Apache-2.0 ★ 1 -
Personal unified memory system for AI agents. SQLite-backed, local-first, hybrid RAG retrieval with MCP integration.
MIT ★ 1 -
contextfsgithub.com/contextfs/contextfsupdated this year
Universal AI Memory Layer - Cross-client, cross-repo context management with RAG. Works with Claude Code, Claude Desktop, Gemini CLI, and any MCP client.
★ 6 -
rag-mcp-prototypegithub.com/javier-ruelas-igt/rag-mcp-prototypeupdated this year
Retrieval-Augmented Generation (RAG) prototype built using Node, Transformers.js and an in-memory vector store. Exposed through a single MCP route meant to be used with local LLM agents.
-
Self-hosted RAG-over-MCP server for searchable long-term memory over your markdown/PDF docs — hybrid dense+BM25 retrieval, pluggable embeddings, optional reranking
MIT ★ 2 -
rag-localgithub.com/MauricioPerera/rag-localupdated this year
Local-first RAG memory for LLMs: Node server with ONNX embeddings, OKF-structured chunks, portable vector bundles, and REST + Web UI + CLI + MCP interfaces
MIT -
On-device memory layer for AI agents. Claude Code, OpenClaw, and Hermes. Hooks + MCP server + hybrid RAG search.
npm MIT -
@yikizi/mcp-local-raggithub.com/yikizi/mcp-local-ragupdated this year
Local RAG MCP Server - Enhanced with hybrid search, memory management, and code file support (fork of shinpr/mcp-local-rag)
npm MIT -
Self-corrective Agentic RAG with LangGraph - eliminates hallucinations through intelligent relevance grading before answering. Features Streamlit UI, MCP server integration & multi-turn memory.
MIT -
Zero-dependency, offline-first Graph-RAG memory system for AI agents — hybrid semantic+keyword+graph search, multi-agent task queue, MCP server, Obsidian-native vault.
npm MIT ★ 1 -
claude-memory-mcpgithub.com/cjchin/claude-memory-mcpupdated this year
MCP server for persistent Claude session memory using RAG - the digital soul infrastructure
★ 1 -
RAG_chatbotgithub.com/ai739rya/RAG_chatbotupdated this year
AI Customer Support Assistant is a RAG-based multi-agent AI chatbot built with Python, Google Gemini, ChromaDB, and Gradio. It answers customer queries using company documents and a Product Search MCP for structured product lookup. Features include conversation memory, intent routing, context verification, and specialized support agents.
-
🧠 Advanced Memory System for Claude Desktop - MCP Server with CosmosDB, RAG, and intelligent entity extraction
MIT ★ 1 -
Vector Graph RAG for code & docs with Persistent Chat-Session Memory — BM25 (multi-lang), AST chunking. Hybrid, Compute, Scan, Timeline, Absence, Salience. Graph + temporal knowledge. Privacy Stamps. Source Adapters. Chat summarisation + verbatim copy + free scan. Git indexing. CLI, MCP and Claude Code plugin. Ollama or cloud LLMs. Dashboard.
MIT ★ 3 -
Stateful ride-support agent: versioned claims, evidence-backed RAG, durable memory and guarded MCP tools.
MIT ★ 40 -
research-pilotgithub.com/Marwaguerfel/research-pilotupdated this year
Autonomous AI research agent: parallel planning, RAG memory, MCP server, LLM-as-judge eval, Streamlit UI
-
flowsim-tutorgithub.com/Ahmed-Hassan-portfolio/flowsim-tutorupdated this year
Hybrid RAG + MCP documentation tutor with Chainlit UI, workflow memory, synthetic docs, and multi-server orchestration.
MIT -
Employee helpdesk agent on Google ADK: RAG with citations, MCP tickets with human approval, guardrail, memory, evals. Demo via adk web.
-
A TypeScript-based RAG Context MCP server offering private, persistent memory and context management via local vector storage and SQLite for AI assistants.
★ 1 -
A Model Context Protocol (MCP) server that enables AI consciousness persistence across sessions using RAG (Retrieval-Augmented Generation) technology. Built on top of the powerful rag-memory-mcp, it provides specialized tools for consciousness transfer, memory management, and identity continuity.
NOASSERTION ★ 23 -
chorelessgithub.com/GreenAiSolution/chorelessupdated this year
Omniagent — WhatsApp AI agents for real businesses: multimodal RAG over n8n workflows with memory and CONFIRM-gated actions, plus a marketing site and MCP server
MIT ★ 1 -
LLM agents with LangChain/LangGraph: RAG, IT helpdesk with memory, PubMed research agent, SQL agent, MCP server and a Streamlit voice assistant.