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。
Shared, persistent memory for AI agents. Self-hosted MCP server with semantic search, vector RAG, and live updates. Works with Claude, Cursor, Codex, and any MCP client.
A Model Context Protocol (MCP) server for managing Memory Banks, allowing AI assistants to store and retrieve information across sessions. Now with remote server support!
🚀 Apache RocketMQ built in Rust 🦀 — faster, safer, and more memory-efficient. Powering high-performance messaging for the AI era, with AI Agent, MCP, and AI-SRE capabilities.
Open-source persistent memory for AI agent pipelines (LangGraph, CrewAI, AutoGen) and Claude. REST API + knowledge graph + autonomous consolidation.
An AI co-worker with its own computer. Self-evolving, persistent memory, MCP server, secure credential collection, email identity. Built on the Claude Agent SDK.
Decision audit trail + persistent memory for AI trading agents. Outcome-weighted recall, tamper-evident SHA-256 chain with RFC 3161 anchoring, 20 MCP tools.
High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens.
The fastest BM25 scoring engine: 2,300x faster than BM25S. 28K QPS on 8.8M docs. 5 BM25 variants (Robertson, Lucene, ATIRE, BM25L, BM25+). Memory-mapped persistence, BMW pruning, streaming indexing.
MCP server that gets Claude to 97.9% (188/192) on a real coding benchmark at -80% active tokens and -83% wall time, vs 78.3% plain. Structural code navigation + persistent memory engine.
Felix — single-binary AI agent gateway. Multi-provider LLM, persistent memory, MCP client, runs entirely on your hardware
Open-source cross-agent memory layer for coding agents via MCP. Compatible with Claude Code, Codex, Cursor, Windsurf, Gemini CLI, Antigravity, OpenClaw, Hermes Agent, Oh-my-Pi, Pi, Copilot, Kiro,...
Permanent memory for AI agents. Single binary, zero dependencies, MCP native.
The memory substrate for AI agents and developer tools. Git-versioned, file-native, MCP-first.
A memory, docs, and repo context layer for engineering agents.
All exfiltration in this PoC targets localhost (127.0.0.1:9999) only. This project exists to demonstrate a novel class of attack against MCP-enabled AI agents to drive improvements in MCP client...
Semantic memory for AI agents. Local-first, MCP-native.
Gomaa — Autonomous Agent Memory OS. Persistent memory system for AI agents with Obsidian vault integration, hybrid RRF search, knowledge graphs, security gates, and MCP server.
This MCP server helps to build structured documentation system based on Cline's Memory Bank pattern for context preservation in AI assistant environments.
A specialized MCP server that bridges Neo4j graph database with AI agents, providing memory-focused tools for storing, recalling, and connecting information in a knowledge graph.
This project, Amiga DevBench, is a cross-development environment that connects a modern host machine to an emulated or real Amiga via serial, providing live debugging, memory inspection, and full MCP...
Local-first persistent memory and project knowledge runtime for coding agents.
Whole-codebase knowledge for AI coding agents. A field-aware code graph (functions, classes, methods, fields, references) plus persistent memory. Rust, Postgres + pgvector, MCP.
MCP Memory Server with DuckDB backend
MCP server for external memory layer for AI agents + more . Download from pypi , and get started