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/9

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

193–216 of 330 · ranked by trust score, then stars

Qdrant

mhalder/qdrant-mcp-server

!CAUTION D

MCP server for semantic search using local Qdrant vector database and OpenAI embeddings

★ 364 destructivestdio

open-memex

stoneskin/open-memex

✕BLOCK D

Local-first memory layer for AI coding agents — Markdown as source of truth, MCP server + CLI, human-reviewed capture, team knowledge via git PRs.

★ 42 writestdio

Iai

codeabra/iai-mcp

!CAUTION D

A cyber brain for your AI. It never forgets a detail, remembers exactly what you said, and learns how you work over time. Free, local, works with Cursor, Claude Code, Codex, OpenClaw, Hermes and more. MIT.

★ 9012 writestdio

Mengram

alibaizhanov/mengram

✕BLOCK D

Human-like memory for AI agents — semantic, episodic & procedural. Experience-driven procedures that learn from failures. Free API, Python & JS SDKs, LangChain, CrewAI & OpenClaw integrations.

★ 2042 destructivestdio

Kindex

jmcentire/kindex

!CAUTION D

Knowledge index that learns from your conversations

★ 353 readstdio

Synaptic Memory

plateerlab/synaptic-memory

!CAUTION D

Knowledge graph + MCP tool server for LLM agents with hybrid retrieval, live DB sync, Korean FTS, and memory feedback.

★ 333 destructive

memtomem-stm

memtomem/memtomem-stm

✕BLOCK D

Short-term memory proxy gateway with proactive memory surfacing for AI agents

★ 514 readsse

obsidian-llm-wiki

Statutecontempt951/obsidian-llm-wiki

✕BLOCK D

Convert your Obsidian markdown vault into a six-persona MCP team for local LLM tools to provide cited, accurate insights.

★ 15 readstdio

Memlab

facebook/memlab

✕BLOCK D

A framework for finding JavaScript memory leaks and analyzing heap snapshots

★ 5,06721 writestdio

YourMemory

sachitrafa/yourmemory

✕BLOCK D

Agentic AI memory with Ebbinghaus forgetting curve decay. +16pp better recall than Mem0 on LoCoMo.

★ 269Not listed in sourcestdio

Mnemo Cortex

guymanndude/mnemo-cortex

!CAUTION D

Open-source cognitive coprocessor with active memory for AI agents — persistent recall, semantic search, overnight dreaming, verified facts, encrypted USB sync. MCP server; works with Claude, ChatGPT, and any local LLM. Built by one maker and his agents.

★ 1574 writestdio

Gnosis

nicholasglazer/gnosis-mcp

✕BLOCK F

Zero-config MCP server for searchable documentation (SQLite default, PostgreSQL optional)

★ 291 destructivestdio

wordcell

hraness/wordcell

!CAUTION D

Wordcell keeps decisions, plans, and sources as Markdown beside your code, so coding agents can find them from the file they are about to change.

★ 161 destructivestreamable-http

iai Personal Memory Engine

codeabra/iai-personal-memory-engine

!CAUTION F

A cyber brain for your AI. It never forgets a detail, remembers exactly what you said, and learns how you work over time. Free, local, works with Cursor, Claude Code, Codex, OpenClaw, Hermes and more. MIT.

★ 8962 writestdio

Ditto

ohad6k/ditto

!CAUTION F

Mine your Claude Code and Codex logs into a local you.md agent profile.

★ 292Not listed in sourcestdio

Emulo

ohad6k/emulo

!CAUTION F

Mine your Claude Code and Codex logs into a local you.md agent profile.

★ 292Not listed in sourcestdio

ClawMem

yoloshii/clawmem

✕BLOCK F

On-device memory layer for AI agents. Claude Code, OpenClaw and Hermes. Hooks + MCP server + hybrid RAG search.

★ 2113 writestdio

Sugar

cdnsteve/sugar

✕BLOCK F

Persistent memory for AI coding agents. Local-first, cross-session context, global knowledge, and optional autonomous task execution.

★ 983 destructivestdio

Sugar

roboticforce/sugar

✕BLOCK F

Persistent memory for AI coding agents. Local-first, cross-session context, global knowledge, and optional autonomous task execution.

★ 983 destructivestdio

Prism

dcostenco/prism-mcp

✕BLOCK F

Persistent session memory for AI coding agents — local-first, with on-device inference, associative recall, and drift detection. Works with Claude Code, Cursor, and Codex.

★ 1573 destructivesse

Prism Coder

dcostenco/prism-coder

✕BLOCK F

Persistent session memory for AI coding agents — local-first, with on-device inference, associative recall, and drift detection. Works with Claude Code, Cursor, and Codex.

★ 1573 destructivesse

Kage

kage-core/kage

✕BLOCK F

Persistent, verified memory for coding agents — so they stop re-explaining your codebase and never act on stale knowledge. Every memory is checked against your actual code; lives in your repo as plain files, shared via git. No account, no DB. Install: npx -y @kage-core/kage-graph-mcp install

★ 401 destructivestdio

Engram Memory

engrammemory/engram-memory-community

✕BLOCK F

The highest-scoring AI memory system ever benchmarked that isn't reliant on LLM reranking. And it's free & burns less tokens.

★ 361 destructivestdio

Engram Memory

engrammemory/engram-memory

✕BLOCK F

The highest-scoring AI memory system ever benchmarked that isn't reliant on LLM reranking. And it's free & burns less tokens.

★ 361 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.