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
Agent OS: the agent gets smarter on its own. We just hold the line: Interview-gated, staged evaluation, budgeted evolution loop.
A MCP client for browser-use
Remote MCP server with auth gated by Azure API Management
A Model Context Protocol (MCP) library for the Zig ecosystem.
MCPCorpus is a comprehensive dataset for analyzing the Model Context Protocol (MCP) ecosystem, containing ~14K MCP servers and 300 MCP clients with 20+ normalized metadata attributes.
tutorial for mcp server development
Build lightweight MCP servers in plain Java with annotations, generated schemas, and no Spring runtime
MCP Manager is an Electron-based desktop application for managing Model Context Protocol (MCP) servers.
A complete PHP implementation of the Model Context Protocol (MCP) with server and client support, STDIO and HTTP transports, and framework integration
An SDK implementing the MCP with Binder for LLM-to-app communication on Android.
A package manager to manage all your mcp servers across platforms
MCP server for LibreNMS management
Agent Skills
Kubernetes operator for managing Hermes agent instances in declarative manner.
永久免 token 费的 openclaw；三个重磅 Skill 大幅提升桌面执行能力；无需安装，开箱即用；支持微信、钉钉等多端接入控制。
Build & prompt Qwen3.x agents in their native dialect — extracted from qwen-code & Qwen-Agent
An opinionated, agentic life-OS for Claude Code — a markdown vault with daily/weekly/quarterly review skills baked in. Includes the feedback layer most templates skip.
剪辑录屏工程中的停顿、误讲、重复与空片段，支持合并补录和按讲述替换屏幕内容。
Autonomous multi-agent workflow system for complex coding tasks.
A "supercharged" implementation of Claude Code Skills – using Haiku prompt analysis/critical skill scoring and skill auto-injection for friction-free, context-driven workflows.
Short devtools brand-voice guide: pillars, do/dont, rewrites, channel notes.
A Claude Code skill for downloading and summarizing videos from Xiaohongshu (小红书/RedNote) using yt-dlp.
Thin, editable harness that lets an LLM control real iOS/Android devices via MobAI. The agent writes what's missing during execution; the harness improves itself every run.
Based on your current lab repository, design your experiement panel.
An Obsidian plugin that can talk to an OpenClaw instance.