Cursor 安装指南
常与开发类 MCP Server 搭配使用的 AI 代码编辑器。
MCP Servers
A self-modifying, self-verifying AI agent with persistent state. Reads its own source code. Plans changes. Tests them in a sandbox before applying.
MCP Server for Ozon marketplace - search products, get details, prices and delivery info
Scan your dev machine for AI agents, MCP servers, IDE extensions, suspicious files, and risky package-manager configs — in seconds.
kali linux mcp,pentest,penetration test
A mcp server that bridges Dune Analytics data to AI agents.
Add vision to text-only models in Opencode (, ) — , no manual file saving.
台灣醫療健康資料整合 MCP 伺服器 整合 ICD-10-CM/PCS、SNOMED CT、LOINC、台灣 FDA 藥品 / 健康補充品 / 食品營養，以及 FHIR R4 IG 授權與驗證工具
188+ local tools for Claude, ChatGPT, Cursor & Grok — Mail, iMessage, Teams, Slack, WhatsApp, OneDrive, Google Drive, Zoom, Outlook, Office. Native macOS, 100% local, no API keys.
MCPSafari: Native Safari MCP Server for AI Agents
The MCP ecosystem has grown to 10,000+ servers, but discovering and installing them remains painful. Existing directories — Glama, PulseMCP, mcp.so — are all closed source.
This MCP server connects your AI agent to — Google's creative suite for image and video generation. Your agent can:
The polished public release — native ComfyUI design system, live activity cards for every agent edit, and multi-tab support. Search in ComfyUI-Manager to install, or see the docs.
Agent Skills
《深入理解 AI Agent：设计原理与工程实践》（李博杰 著）开源主仓库：全书正文、编译版 PDF 与按章配套代码
A reactive programming library for JavaScript
SigNoz is an open-source, OpenTelemetry-native observability platform for your team and their AI agents.
Production-ready skill for building, testing, and automating iOS apps. 27 scripts optimized for both human developers and AI agents.
🔬 Harness Vibe Research with Self-evolving AI Scientists
A curated collection of production-ready Hermes Agent skills — brainstorming, PRD workflows, debugging, Apple integrations, MLOps, document processing, and more.
The open sharing protocol for the agentic era. A Linux Foundation AI & Data Project
这个仓库源于我使用 Codex 的日常需求。写论文不是单点任务，而是一条从构思、实验、写作、审稿到 rebuttal 的长链路；每一步都需要 AI 有边界、有证据、懂学术表达。因此这个仓库把 组织成当前 7 个模块、27 个可触发 Skills：
A streamlined and customizable framework for efficient large model (LLM, VLM, AIGC) evaluation and performance benchmarking.
A collection of interesting libraries and tools for Avalonia project.
Xiaomi Miloco
From Chain-of-Thought prompting to OpenAI o1 and DeepSeek-R1 🍓