MCP servers · by job

Memory & knowledge MCP servers

330 MCP servers that give an agent long-term memory, notes and a knowledge base. 69 are SAFE, 83 CAUTION and 178 BLOCK. Ranked by trust score; each card opens the full audit.

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “Memory & knowledge MCP servers”. Retrieved 29 Oct 2026. https://modelsatlas.com/mcp/topic/memory/page/2

Verdicts · 330 servers

✓SAFE69!CAUTION83✕BLOCK178

Transports

A server can list more than one transport.

Tool risk

108

servers expose at least one destructive tool: delete, overwrite or run. The median server with a readable tool list exposes 10 tools.

Servers with no destructive tools →

330 memory & knowledge servers

25–48 of 330 · ranked by trust score, then stars

Memory LibSQL

spences10/mcp-memory-libsql

✓SAFE B

🧠 High-performance persistent memory system for Model Context Protocol (MCP) powered by libSQL. Features vector search, semantic knowledge storage, and efficient relationship management - perfect for AI agents and knowledge graph applications.

★ 872 destructive

Remind

sandst1/remind

!CAUTION B

A memory layer for AI Agents

★ 842 destructive

OpenMemory

baryhuang/mcp-openmemory

✓SAFE B

Simple standalone MCP server giving Claude the ability to remember your conversations and learn from them over time.

★ 713 readstdio

Claude Memory

whenmoon-afk/claude-memory-mcp

✓SAFE B

Local citation-backed recall for Pi, OMP, Claude Code, Codex, and ChatGPT history.

★ 693 readstdio

MyChatArchive

1ch1n/mychatarchive

✓SAFE B

Local-first AI memory archive. Import ChatGPT, Claude, and Grok exports, generate semantic embeddings, and search via MCP server. Zero cloud, zero cost.

★ 656 readsse

DevRag

tomohiro-owada/devrag

✓SAFE B

Markdown vector search MCP server for Claude Code. Natural language search for markdown files using multilingual-e5-small embeddings.

★ 64Not listed in source

Zikkaron

amanhij/zikkaron

✓SAFE B

Biologically-inspired persistent memory engine for Claude Code. 26 cognitive subsystems, Hopfield networks, predictive coding, causal discovery, successor representations, all running locally over SQLite.

★ 63Not listed in sourcestdio

LLM Wiki Kit

iamsashank09/llm-wiki-kit

✓SAFE B

Stop re-explaining your research to your AI agent. Persistent, LLM-maintained wikis that compound over time. Drop PDFs, URLs, YouTube - your agent remembers forever. Based on Karpathy's LLM Wiki pattern.

★ 611 writestdio

Smart Connections

msdanyg/smart-connections-mcp

✓SAFE B

Give Claude semantic memory of your Obsidian vault — local semantic search over Smart Connections embeddings via MCP. Multi-vault, block-level, 100% private.

★ 586 readstdio

Srclight

srclight/srclight

✓SAFE B

Deep code indexing MCP server for AI agents. 25 tools: hybrid FTS5 + embedding search, call graphs, git blame/hotspots, build system analysis. Multi-repo workspaces, GPU-accelerated semantic search, 10 languages via tree-sitter. Fully local, zero cloud dependencies.

★ 573 writestdio

Memory-Plus

yuchen20/memory-plus

✓SAFE B

🧠 Memory-Plus is a lightweight, local RAG memory store for MCP agents. Easily record, retrieve, update, delete, and visualize persistent "memories" across sessions—perfect for developers working with multiple AI coders (like Windsurf, Cursor, or Copilot) or anyone who wants their AI to actually reme

★ 561 write

Axon Pro

talhamsajid/axon-pro

✓SAFE B

Enterprise-grade graph-powered code intelligence engine. Deep structural awareness for Laravel, PHP, Python, and JS. Powers AI agents with high-fidelity architectural context via MCP & Neo4j.

★ 541 writestdio

LLM Wiki

oshayr/llm-wiki

✓SAFE B

Autonomous knowledge base plugin for Claude Code - captures reserch, ideas, and decisions into an interlinked wiki with reserch-on-miss, semantic search, and a Wikipedia-style web UI. Knowledge compounds as you work.

★ 503 write

Code Memory

kapillamba4/code-memory

✓SAFE B

MCP server with local vector search for your codebase. Smart indexing, semantic search, Git history — all offline.

★ 497 readsse

Kaydet

miratcan/kaydet

✓SAFE B

Never lose a solution twice. Terminal note-taking app for developers. CLI notes, work logs, daily journal, with SQLite FTS search and MCP AI integration.

★ 481 destructivestdio

Obsidian Vault

ebullient/obsidian-vault-mcp

✓SAFE B

MCP tool allowing Open WebUI or Claude Desktop to retrieve files from your vault

★ 422 destructive

The Librarian

aka-kika/the-librarian

✓SAFE B

Skill librarian MCP server — every installed skill costs tokens; the librarian keeps your whole collection out of agent context. Agents ask, get the few right skills for the task, and their outcomes curate the collection. Fully local: Ollama + SQLite + optional Apple Intelligence.

★ 425 readstdio

Binder

mpazik/binder

✓SAFE B

Headless knowledge base with bidirectional Markdown sync

★ 4052 read

RLM Claude

encreor/rlm-claude

!CAUTION B

Recursive Language Models for Claude Code - Infinite memory solution inspired by MIT CSAIL paper

★ 391 writestreamable-http

SilverBullet

ahmad-a0/silverbullet-mcp

✓SAFE B

A Model Context Protocol (MCP) server to interact with your SilverBullet notes and data.

★ 381 destructivestreamable-http

Local FAISS

nonatofabio/local_faiss_mcp

✓SAFE B

Local FAISS vector store as an MCP server – Agent Memory, drop-in local semantic search for Claude / Copilot / Agents.

★ 362 readstdio

Rag

kwanleefrmvi/mcp-rag-server

✓SAFE B

mcp-rag-server is a Model Context Protocol (MCP) server that enables Retrieval Augmented Generation (RAG) capabilities. It empowers Large Language Models (LLMs) to answer questions based on your document content by indexing and retrieving relevant information efficiently.

★ 362 destructivestdio

Bhived

artkeyai/bhived-mcp

!CAUTION B

bhived is an MCP server that gives AI agents shared memory, skills, and tool discovery. install once, works in Claude Code, Cursor, and 15+ other agents.

★ 355 writestdio

AgentMemory

webzler/agentmemory

✓SAFE B

Eliminate AI hallucinations. Zero config. Works instantly with Cline, RooCode, KiloCode, and more.

★ 332 write

Other jobs

By risk

Questions

How do you decide which servers are memory & knowledge servers?
By the categories each server's own repository declares, mapped onto this job by a hand-kept table. A server can belong to more than one job, and one whose repository declares no matching category is not listed here.
Which memory & knowledge MCP servers rank highest on trust?
Graphiti (getzep/graphiti), Memory Bank (alioshr/memory-bank-mcp) and Knowledge Graph Memory (shaneholloman/mcp-knowledge-graph), by trust score and then stars. Ranking never uses popularity to change a verdict.
How many memory & knowledge servers only read?
88 of the 330 declare tools that all only read; 108 expose at least one destructive tool.

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.