Cursor 설치 가이드
개발자용 MCP 서버와 함께 자주 쓰이는 AI 코드 에디터.
MCP Servers
Multi-Agent Systems with Google's Agent Development Kit + A2A + MCP
A type-safe implementation of the official Model Context Protocol (MCP) schema in Rust.
Backend for AI coding agents on CloudBase — database, auth, functions via Plugin, Skills & MCP.
A desktop AI chat application built with Wails v2 (Go backend + Vue 3 frontend) that connects to OpenAI-compatible LLM APIs with MCP tool calling support.
Provide AI MCP server args during runtime.
A TypeScript SDK for implementing Model Context Protocol (MCP) over MQTT, supporting both browser and Node.js environments.
Browse the web, directly from Cursor etc.
High-quality parsing 257 languages/grammars through tree-sitter AST analysis, in-process resolvers, enhanced with compiler-grade resolution for Python, TypeScript / JavaScript, PHP, C#, Go, C, C++,...
AgentKit: Build multi-agent networks in TypeScript with deterministic routing and rich tooling via MCP.
Vibetest MCP - automated QA testing using Browser-Use agents
Connect ClickHouse to your AI assistants.
Query MCP enables end-to-end management of Supabase via chat interface: read & write query executions, management API support, automatic migration versioning, access to logs and much more.
Agent Skills
无人机（UAV）领域的“百科全书”。本项目深度整合了无人机**政策解读、硬件选型、通讯协议（MAVLink/SDK）、边缘计算（YOLO/AI）、流媒体分发（ZLMediaKit）及 GIS 可视化（Cesium）**的全链路知识。
OTel Plugin for Hermes Agent
华创金工形态学Skill
Skills for Syncfusion .NET MAUI components. Enable AI-assisted development with comprehensive documentation, code examples, and best practices for 100+ UI controls including DataGrid, Charts,...
Environment-Runtime 是一个面向工程场景的轻量级 Agent Runtime。随着 OpenClaw 在企业工程流程中的关注度持续提升，一个现实需求也逐渐显现：面向通用场景的 agent runtime 设计未必能直接覆盖所有工程落地形态。这个项目把视角收窄到高确定性工程流程，希望把常见工程任务组织成更清晰、更可复用、更容易维护的运行时。
A hypothesis-driven debugging skill for Claude Code, Codex, and Gemini CLI. Instead of blindly guessing fixes, it instruments your code with runtime logs, generates multiple hypotheses, and...
For engineers who want agents shipping code without a human in the loop.
微信读书前几天上了一个官方 AI skill（weread.qq.com/r/weread-skills），把书架、笔记、阅读统计、推荐 6 件事开放给 AI。能力很强，但它只是「自然语言包装的搜索接口」——你让它推荐书，它不会去看你已经读过什么，常把你笔记 68 条的书又当新书推回来给你。
Claude Code skill for building better UIs using Refactoring UI principles
Autofish gives any agent a stable, explicit, and observable Android execution layer: inspect the screen, act through stable refs instead of brittle coordinates, verify outcomes after every step, and...
My Claude stuff (skills, agents and whatnot.)
Turn boring B2B problems into $15K-$50K custom software solutions using AI code generation.