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。
Local MCP server that helps coding agents stop re-reading the same code every turn. Repository intelligence, cache-write optimization, and long-term session memory. 100% local. No API keys.
Machine-readable architecture decision records. Git-native decision memory and governance for human and agent-authored plans -- lint, CI, and MCP.
Founders OS - CRM, tasks, finances, feeds, and memory for founders, as an MCP server.
BrainFlow - Shared Team's Memory - Company Brain - MCP server documentation and setup guide
Custom minimal AI agent with persistent memory, MCP tools, and Discord
Agent Orchestration: MCP server enabling multi-agent collaboration with shared memory, task queue, resource locks, Cursor rules, and AGENTS.md workflows.
Hands-on offensive-security labs for AI agents — MCP tool poisoning, cross-server shadowing, RAG injection, agentic memory attacks, and a runnable five-stage MCP→A2A kill chain.
An MCP server allowing AI assistants to use a Neo4j knowledge graph as their primary, dynamic instruction manual and long term project memory with adaptive templating and autonomous tool development...
Persistent, searchable long-term memory for AI agents. MCP-native. Works with ChatGPT, Claude, Cursor, and any MCP client.
AI-first, zero-dependency JavaScript database. Vector search, agent memory, MCP server, and encryption built in. Node.js, Bun, Deno, browsers, and edge runtimes.
Memory you can edit. Watchers that wake an idle Pi agent without model polling. A persistent side conversation, searchable history, optional archive encryption, native MCP and explicit controls.
A local MCP (Model Context Protocol) server for portable, long-term agentic memory — a thumb drive for your AI context.
Validated, private, shareable knowledge-graph memory for AI — per-tenant, write-gated, PostgreSQL-authoritative, served over MCP.
PS4/PS5 Windows workbench: memory scanning, MCP, Ghidra RAM exports, FTP, PKG installs, console controls and saves. Tested PS4 10.01 / PS5 13.60.
An enterprise-grade travel planning intelligent agent system built by Agno framework. Integrating advanced functionalities including MCP, Skills, Memory, Knowledge Bases, Agent Teams, and Workflows.
A powerful MCP memory using a knowledge graph powered by elastic search
In-memory graph database and Gremlin traversal engine in Rust: browser playground, CLI, MCP server for AI agents, durable store, Python bindings.
MCP server for NVIDIA GPU metrics give AI agents real-time access to GPU utilization, memory, temperature, and power
A local MCP server that gives Claude a persistent memory, a private search index for your files and chats, encrypted secret storage, cost visibility across every LLM you use, and a bridge to every...
The standard FastMCP framework faces significant challenges in production environments: - : Traditional FastMCP servers maintain state in memory, making horizontal scaling difficult - : Serverless...
Unified Context MCP is a memory and retrieval layer for AI agents that turns conversations and tool outputs into structured, reusable context.
Local-first MCP server that gives AI agents durable repo memory and fast semantic code context.
A persistent memory MCP server for AI coding agents — stores, searches, and retrieves atomic learnings so agents retain knowledge across sessions.
A **bulletproof proxy server** for MCP (Model Context Protocol) that aggregates multiple MCP servers with comprehensive memory leak prevention and reliable HTTP/SSE transport.