Cursor 설치 가이드
개발자용 MCP 서버와 함께 자주 쓰이는 AI 코드 에디터.
MCP Servers
A Model Context Protocol (MCP) server that provides web search capabilities through DuckDuckGo, with additional features for content fetching and parsing.
One home for every agent. A free, open-source app to manage all your AI coding agents — desktop, CLI, or web.
Lighweight CLI to interact with MCP servers
Draw.io Model Context Protocol (MCP) Server
Telegram MCP server powered by Telethon to let MCP clients read chats, manage groups, and send/modify messages, media, contacts, and settings.
Integrate QuantConnect's research environment, statistical analysis, and portfolio optimization into your AI workflows. Locally hosted, secure & capable of dramatically improving productivity
A modern desktop application for managing Model Context Protocol (MCP) servers across multiple AI agents
mcp-client-go is a Golang client library for the . It allows developers to register and interact with various MCP-based services such as Amap (Gaode Maps) using a unified API.
A Model Context Protocol server that provides MySQL database operations. This server enables AI models to interact with MySQL databases through a standardized interface.
A C library for embedding Apple Intelligence on-device Foundation models in any programming language or application with full support for native tool calling and MCP.
A Model Context Protocol server implementation for interacting with Salesforce through its REST API using jsforce.
The Axiom MCP Server connects AI assistants to your Axiom observability data using the Model Context Protocol (MCP). This repository contains:
Agent Skills
Built for humans, AI agents, and CI/CD pipelines.
xianxia-cinematic-video-director 是一个面向 Codex / Agent Skills 体系的东方仙侠电影视频导演 Skill。它将场景构想、图片提示词、关键帧或参考视频，扩展为具有故事推进、空间连续性、明确运镜和稳定首尾状态的多镜头视频方案。
每个 Skill 都是一个可安装的思维操作系统，不是语录合集。 安装后可在支持 Agent Skills 的 AI 助手中，以该人物的视角分析问题、审视决策、提供反馈。
Jetpack Compose audit + coding-agent skills for Claude Code, Codex, Cursor, and Anthropic-style skill loaders.
40 SAP development plugins with evidence-tracked verification
*Plug in any agent (Claude · Codex · Gemini · Hermes · …), any model (Claude · GPT · Gemini · DeepSeek · Doubao · MiMo · MiniMax · Qwen · OpenRouter · local Ollama / mlx-lm · or any OpenAI-compatible...
- 修复 AskUserQuestion 选项点击后只在界面显示已响应、却没有真正发送给模型的问题；答案现在按问题原文组装，并通过 Claude Code 控制协议回传。 - 修复 v1.0.7 过滤掉部分历史会话的问题；即使会话尚未写入助手回复，也会继续保留在历史列表中，避免旧对话莫名消失。
MapStage live tuner: map/globe, satellite, hypsometric relief, region isolate, Mapterhorn DEM, JSON presets.
grill-for-unknowns combines docs/source-grounded plan interrogation with the “finding your unknowns” strategy: known knowns, known unknowns, unknown knowns, and unknown unknowns.
Academic Figure Skill 面向学术级科学图表生成Skill，可自动完成从数据解读到顶刊格式图表生成的全流程。 问题驱动 · 8 步闭环工作流 · 29 种图型 · 四轮 QA 协议 · 矢量 PDF 交付 · 统计报告 项目介绍 · 安装与使用 · 图表类型 · 工作流 · 项目结构 · 质量评估 · 贡献指南 · English
A skills pack that turns an academic paper PDF into any of several promotional artifacts, covering the main forms of paper dissemination:
Agent skills for fal.ai. The default execution path is the genmedia CLI: discover an endpoint, inspect its schema, run it, poll status when needed, and download outputs.