Cursor Руководство установки
AI-редактор кода, часто используемый с developer MCP.
MCP Servers
A Model Context Protocol (MCP) server that provides debugging capabilities through the Debug Adapter Protocol (DAP).
A Model Context Protocol (MCP) server implementation that provides database interaction and business intelligence capabilities through IoTDB.
is a Model Context Protocol (MCP) server that connects AI agents with the Zscaler Zero Trust Exchange platform. for security, requiring explicit opt-in to enable write operations.
This is a Model Context Protocol (MCP) tool that allows Claude to interact with Microsoft Outlook for macOS.
A JetBrains IDE plugin that exposes an , giving AI coding assistants full programmatic control over the debugger.
Model Context Protocol (MCP) is a standardized protocol for managing context between large language models (LLMs) and external systems.
📝 : MCP Servers over Streamable HTTP (Step-by-Step)
A Model Context Protocol (MCP) server for comprehensive OPNsense firewall management. This server enables AI assistants like Claude to directly manage firewall configurations, diagnose network...
This project implements a Model Context Protocol (MCP) server that interacts with Shopify Dev. This protocol supports various tools to interact with different Shopify APIs.
ThingsPanel IoT Platform's MCP (Model Context Protocol) Server.
MCP Server for interacting with the Figma API. This server provides a complete set of Figma API methods through the Model Context Protocol.
A Model Context Protocol (MCP) server implementation for LunchMoney, providing programmatic access to personal finance management through LunchMoney's API. Also available as an MCP Bundle (.
Agent Skills
An agent skill for managing isolated execution environments
Skills, rules, and validation hooks that teach AI coding agents to generate correct UdonSharp code
Elves is an open-source Agent Skill for handing planned development or research work to a separate worker without locking the run to one model provider.
開源的 知識庫，分成 22 個主題類別。每個 skill 都是獨立的 Markdown 檔案（SKILL.md），遵循 Claude Agent Skills 規範，部分附帶純 Python 腳本做確定性計算。
Browser Control lets trusted coding agents run Playwright against your existing Chromium-family browser.
Blueprint helps agents decide what to build, make focused changes, test them, get an independent review, and open pull requests.
Guides and production-ready commands for Claude Code: skills, subagents, hooks, memory, custom commands, and conversation-history tooling.
PavedPath Code（代码版）is a reusable Skill for finding proven implementation paths from GitHub and open-source evidence, then adapting them to local software engineering problems.
is a config-driven dev tool for Elixir projects that manages your AGENTS.md file and agent skills from dependencies. It:
The open-source desktop AI agent that gets work done — an agent that plans and self-corrects, agentic visual workflows, generative UI, and 100+ offline tools in a single self-hostable stack.
仕事の日本語を、読みやすくわかりやすく書く・直すための Agent Skill です。議事録・調査レポート・社内ガイド・リサーチメモ・スライド構成といった仕事の文書から、note・ブログ・エッセイまで扱います。
一个 AI 编程助手 Skill（支持 Claude Code / Codex / OpenClaw），用自然语言描述你的设计需求，即可生成可直接运行的 Vivado / Vitis HLS / Vitis Unified / PetaLinux 脚本。覆盖从 HLS 算法到启动镜像的完整 FPGA/MPSoC 设计流程。