MCP Server 排行

A curated list of open source repositories for AI Engineers

Safe local execution layer for AI agent tools. Build, validate, and publish MCP tools with a no-pass-no-run workflow — cross-platform desktop app powered by Spring AI.

Deploy a complete self-hosted AI stack with Docker Compose: Ollama, LiteLLM, AnythingLLM, Whisper, WhisperLive, Kokoro, Embeddings, Docling and MCP Gateway. Local-first, private by default, with lightweight stacks, optional HTTPS and NVIDIA CUDA acceleration. Multi-arch: amd64, arm64.

AZMX AI — The sovereign agent platform.

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

🐙 Drop-in tools that give AI agents reliable, permission-aware access to external systems.

AI 应用合规网关 · 一行命令体检 AI 项目的「数据出境 / 硬编码密钥 / 个人信息暴露」（网安法·PIPL·等保2.0·数据出境·AI标识），并给出境内模型替代建议；可作运行时防护拦截注入与数据外泄 · 中文优先 · 零依赖 · 开源

Production-ready Next.js template for building AI agents with LangGraph.js. Features MCP integration for dynamic tool loading, human-in-the-loop tool approval, persistent conversation memory with PostgreSQL, and real-time streaming responses. Built with TypeScript, React, Prisma, and Tailwind CSS.

Lightweight graph database with relational, vector, and MCP support, designed to power knowledge and artificial intelligence persistence and retrieval.

Claude Code Prompt Mechanism Visualizer — Electron desktop app

Context Engineering: Build Consistent, Accurate, Predictable AI Systems

Practices, protocols, and skills for AI-driven software development. Skills and safety hooks for Claude Code, Codex, OpenCode, Cursor, Antigravity, and any agent supporting the Agent Skills standard.

Drive Google Flow from the command line: Veo video and Imagen images, scripted, batched and pipeline-ready. Ships an MCP server so coding agents can drive it too, giving you and your agents full programmatic control over generation. Unofficial, alpha, not affiliated with Google.

A general-purpose Python framework for building LLM agents and multi-agent systems. "Four lines of code, an agent with memory."

One TypeScript interface for 24+ LLM providers — swap providers without rewriting. MCP-native (connect any MCP server), voice (TTS/STT/realtime), RAG, memory, file processors. Production-origin: powers Tara, Yama, and Clairvoyance at Juspay.

Find out what your coding agents already know. Docmancer indexes the memory, rules, and instructions Claude Code, Codex, Cursor, and Gemini wrote on your machine, then carries the durable parts to every agent. It is local-first and under MIT license.

Rails Engine with MCP compliant Spec.

Circuitron: Agentic PCB Design Accelerator — Generate, plan, and layout circuits from natural language prompts.

Multi-Agent,MCP,RAG,SpringAI1.0.0,RE-ACT

Own your AI memory — import ChatGPT, Claude and Gemini exports, see what each AI knows about you. Checkpoint/restore and cross-model continuity for agents.