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
furi is an easy to use, CLI & API for MCP management.
This is an example of an application that's exclusively accessible via Model Context Protocol (MCP).
A single-binary MCP server that connects Claude Desktop and Claude Code to Microsoft Outlook via the Microsoft Graph API.
An MCP server that queries public SearXNG instances, parsing HTML contents into a JSON result
Enhanced note taking for AI Agents with supervision.
A simple NextJS MCP client with sensible keybindings
A collection of samples, tools, and resources for building applications with SharePoint Embedded — a document storage API built on Microsoft 365.
Local-first creative studio with 37 model routes, transparent costs, local archives, and MCP access.
Intercept AI requests, track usage, inject MCP tools centrally
GCO is a platform that spins up EKS Auto Mode clusters across AWS regions, wired together with Global Accelerator for low-latency routing.
Опубликовано на Infostart: https://infostart.ru/1c/tools/2720241/
Your AI assistant now remembers everything. Forever. Across every conversation.
Agent Skills
(@daedalium) — solo capitalist and venture builder operating as a "Holding Company of One" from Dubai. Early investor in Stripe, Algolia, PayFit, Trainline.
AI-powered hardware development platform — design, verify, synthesize, and deploy working RTL with natural language.
MIT licensed · Works with Claude Code & Codex · Pure Markdown + two small Python scripts, no dependencies
A practical configuration kit for Claude Code, Codex, and other coding agents. It contains architectural principles, enforcement hooks, skills, drop-in rules, starter templates, and dynamic-workflow...
recursive-mode is an installable skill package for structured AI-assisted software development.
Web 界面的源码、构建脚本、core/registry 实现与 Rust CLI 都在私有仓 HaddenHunter/SkillForge-Core。本仓 main 分支**（技能清单、文档、镜像配置等）；可访问的静态站点由 Core 仓的 Actions 构建后，跨仓推送到本仓的 gh-pages 分支，由 GitHub Pages 服务。
Claude Code skills and sub-agents for .NET Developers
AI agent evaluation toolkit for Copilot Studio. Plan evals, generate test cases, interpret results, and triage failures — from Claude Code or GitHub Copilot.
https://github.com/user-attachments/assets/8bc180a3-0baf-473d-87c9-6aaacce302f2
This tool reads KakaoTalk's local database and automates the UI via macOS Accessibility APIs. It does not reverse-engineer the KakaoTalk protocol or call any Kakao APIs. See Disclaimer for details.
pi-subagents is a highly curated multi-agent framework for Pi agent harness.
Matt Shumer's aim prompt as a slash command — build a game against a named reference. Fill the three paragraphs. Run them. Stop when you stop it.