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 28 Oct 2026. https://modelsatlas.com/mcp/topic/memory

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

1–24 of 330 · ranked by trust score, then stars

Graphiti

getzep/graphiti

✓SAFE B

Build Real-Time Knowledge Graphs for AI Agents

★ 31,0023 destructivestreamable-http

Memory Bank

alioshr/memory-bank-mcp

✓SAFE B

A Model Context Protocol (MCP) server implementation for remote memory bank management, inspired by Cline Memory Bank.

★ 9212 writestdio

Knowledge Graph Memory

shaneholloman/mcp-knowledge-graph

✓SAFE B

MCP server enabling persistent memory for Claude through a local knowledge graph - fork focused on local development

★ 8902 destructivestdio

Axon

harshkedia177/axon

✓SAFE B

Graph-powered code intelligence engine — indexes codebases into a knowledge graph, exposed via MCP tools for AI agents and a CLI for developers.

★ 8132 writestdio

MegaMemory

0xk3vin/megamemory

✓SAFE B

Persistent project knowledge graph for coding agents. MCP server with semantic search, in-process embeddings, and web explorer.

★ 7071 destructivestdio

Corbell

corbell-ai/corbell

!CAUTION B

AI-powered spec generation and review using multi-repo code graph intelligence for backend teams that ship to production.

★ 6284 readsse

Memento

gannonh/memento-mcp

✓SAFE B

Memento MCP: A Knowledge Graph Memory System for LLMs

★ 4254 destructivestdio

Apple Notes

rafalwilinski/mcp-apple-notes

✓SAFE B

Talk with your notes in Claude. RAG over your Apple Notes using Model Context Protocol.

★ 4152 writestdio

mcp-local-rag

shinpr/mcp-local-rag

✓SAFE B

Local-first RAG server for developers. Semantic + keyword search for code and technical docs. Works with MCP or CLI. Fully private, zero setup.

★ 4142 writestdio

Local RAG

shinpr/mcp-local-rag

✓SAFE B

Local-first RAG server for developers. Semantic + keyword search for code and technical docs. Works with MCP or CLI. Fully private, zero setup.

★ 4052 writestdio

Documentation

andrea9293/mcp-documentation-server

!CAUTION B

MCP Documentation Server - Bridge the AI Knowledge Gap. ✨ Features: Document management • Gemini integration • AI-powered semantic search • File uploads • Smart chunking • Multilingual support • Zero-setup 🎯 Perfect for: New frameworks • API docs • Internal guides

★ 3421 destructivestdio

Ori Mnemos

aayoawoyemi/ori-mnemos

!CAUTION B

Local-first persistent agentic memory powered by Recursive Memory Harness (RMH). Open source must win.

★ 3282 destructivestdio

Ragdocs

hannesrudolph/mcp-ragdocs

✓SAFE B

An MCP server implementation that provides tools for retrieving and processing documentation through vector search, enabling AI assistants to augment their responses with relevant documentation context.

★ 2652 destructivestdio

Vexor

scarletkc/vexor

✓SAFE B

A semantic search engine for files and code.

★ 243Not listed in sourcestdio

Meilisearch

meilisearch/meilisearch-mcp

!CAUTION B

A Model Context Protocol (MCP) server for interacting with Meilisearch through LLM interfaces.

★ 1952 destructivestdio

Ourmem

ourmem/omem

✓SAFE B

Shared Memory That Never Forgets — persistent memory for AI agents with Space-based sharing across agents and teams. Plugins for OpenCode, Claude Code, OpenClaw, MCP Server.

★ 1743 writestdio

Zettelkasten

entanglr/zettelkasten-mcp

✓SAFE B

A Model Context Protocol (MCP) server that implements the Zettelkasten knowledge management methodology, allowing you to create, link, explore and synthesize atomic notes through Claude and other MCP-compatible clients.

★ 1662 destructive

Ombre Brain

p0lar1zzz/ombre-brain

✓SAFE B

For Claude.

★ 1561 destructivestreamable-http

Local Rag

nkapila6/mcp-local-rag

✓SAFE B

"primitive" RAG-like web search model context protocol (MCP) server that runs locally. ✨ no APIs ✨

★ 1345 read

LangGraph AI

piyushagni5/langgraph-ai

!CAUTION B

A comprehensive collection of LangGraph implementations, tutorials, and advanced AI workflows covering Agentic RAG systems, MCP (Model Context Protocol) development, and practical AI application patterns.

★ 1134 writestdio

Needle

needle-ai/needle-mcp

✓SAFE B

Needle MCP Server for easy RAG.Long-term memory for LLMs.

★ 1032 writestdio

loci

IvenKooLab/loci

✓SAFE B

A queryable second brain over your scattered notes and docs - hybrid retrieval (vector + BM25), section-level citations, and an MCP server so AI agents can use it. ~300 lines, no LangChain.

★ 100Not listed in sourcestdio

Mem0

pinkpixel-dev/mem0-mcp

!CAUTION B

A memory system using mem0 for AI applications. Enables long-term memory for AI agents as a drop-in MCP server.

★ 972 destructivestdio

Claudex

kunwar-shah/claudex

!CAUTION B

MCP server with persistent memory + FTS5 search for Claude Code conversation history. Index your ~/.claude/projects/, expose 10 MCP tools, browse via web UI. MIT-licensed.

★ 951 destructivestdio

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.