ベスト＆人気の MCP サーバー
カテゴリ、インストールガイド、ソースで比較できます。
aakarsh-sasi/memory-bank-mcp は [https://github.com/aakarsh-sasi/memory-bank-mcp. からインポートされた MCP サーバーの候補です
yunaga224/obsidian-memory-mcp は [https://github.com/yunaga224/obsidian-memory-mcp. からインポートされた MCP サーバーの候補です
Knowledge graph + MCP tool server for LLM agents with hybrid retrieval, live DB sync, Korean FTS, and memory feedback.
An enhanced MCP (Model Context Protocol) server for intelligent memory and task management, designed for AI assistants and development workflows.
Production-grade vector memory MCP server for Claude Code. Semantic search, per-project isolation, rules enforcement, team sharing via git.
Universal Memory Protocol (UMP) - an open standard for agent memory. The third interop layer beside MCP (tools) and A2A (coordination).
A simple memory implementation
MCP server designed to help you search and analyze your photo library (iCloud - Apple photos)
MCP server providing a knowledge graph implementation with semantic search capabilities powered by Qdrant vector database
🧠 High-performance persistent memory system for Model Context Protocol (MCP) powered by libSQL. Features vector search, semantic knowledge storage, and efficient relationship management - perfect...
Local-first associative memory and vector search for AI agents, with Rust, Python, Node.js, and MCP integrations.
A simple MCP server that stores and retrieves memories from multiple LLMs.
Local-first, auditable memory layer for AI apps and coding agents — Codex, Claude Code, MCP, HTTP, TypeScript, and Python.
Knowledge management MCP server, webapp and winapp; knowledge graphs, im/export, rag, semantic search, skills builder
A Model Context Protocol (MCP) server that provides knowledge graph functionality for managing entities, relations, and observations in memory, with strict validation rules to maintain data...
Never lose context again - persistent memory management system for AI-powered workflows across multiple tools
A lightweight, local-first persistent memory server for AI tools. Stores structured memory entries in SQLite and exposes them over both the Model Context Protocol (MCP) and a plain REST HTTP API
记忆解冻mcp
An mcp server that you can use to store and retrieve ideas, prompt templates, personal preferences to use with you favourite AI tool that supports the modelcontextprovider protocol.
MCP server for on-demand .NET memory profiling with AI-actionable code fix suggestions, collecting heap data in-process over EventPipe
Persistent local memory for Claude and ChatGPT. No cloud, no subscription. Self-hosted RAG over MCP.
Injected x64 Windows DLL + MCP bridge exposing a Cheat-Engine-style live memory debugger as Claude / LLM tools: typed hex view, first/next value scans, AOB, pointer/string scans, reverse pointer...
Agent memory as history: consolidation, anchors, provenance tiers, accountable forgetting, source criticism, narrative integration, canon circulation, social framing — grounded in memory studies...
Unified cross-AI memory: one MCP hub for shared memory, code graph, handoffs, reasoning logs and safe secret references