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

⚠️ This implementation stores OAuth credentials in ./mnt/mcp-creds/ which are currently committed to the repository. Proper OAuth flow for MCP servers is coming soon to the Agencii platform.

The Open Source Analytics and Visibility Layer for ChatGPT Apps and MCP Apps.
The AI Config Plaza. Stop configuring AI tools from scratch. Discover, share, and one-click install verified configurations for MCP servers, Agents, and Prompts.

Git-native API client with encrypted secrets.

Making AI coding assistants experts at Swift and iOS development.

本项目是一个本地 Streamable HTTP MCP Server,用于把 WMPFDebugger 暴露的裸 Chrome DevTools Protocol WebSocket 包装成 MCP 工具,辅助 Codex / Cursor / VS Code Agent 对已授权调试的微信小程序进行安全评估、证据采集和报告整理。

A library built on top of the MCP TypeScript SDK that makes it easier to implement MCP with auth into your MCP client and/or server.

Linked API MCP server connects your LinkedIn account to AI assistants like Claude, Cursor, and VS Code.

A CLI tool for managing MCP servers configurations for MCP clients.

OpenPets is a native macOS desktop pet for visible agent progress, review prompts, completion states, and lightweight animations across local coding tools.

Reliability gateway for AI tool output: schema-stable, secret-safe, pagination-complete JSON for MCP and CLI agents.

Works transparently with , , , and any MCP-compatible agent. Also supports shell command governance and a language-agnostic HTTP API.
Agent Skills

用于把课程当作可验证、可迭代的教学产品:先定义任务与来源,再规划、生成、质检并发布 Markdown/HTML 课程。它提供六类正文写法、课程评价量规与无外部依赖的确定性检查器。

A production-ready library of and for Claude Code — covering thinking frameworks, research, writing, design, data/ML, corporate finance, game theory, fantasy baseball, an evolutionary 10-agent FIFA...

Inclusive-language pass on product/docs copy with rewrites — keep technical accuracy.

Uses Apple Reminders as a bridge between Claude on your phone and Claude Code on your Mac, dispatching agents from new reminders.

中英文学术文本润色与人性化Skill,用于去除 AI 生成的痕迹,同时严格保持事实准确性。

Think Better injects structured decision frameworks directly into your AI prompts.

Market Map agent eval suite for the Reforge AI Evaluation course

DSH Desktop Hub — DeepSeek Harness 桌面管理控制台(Electron + TypeScript)。多 Tab 管理 Harness / Plugin / MCP / Skills,双击即用。

Memory hygiene skills for Hermes Agent — dreaming (3-phase consolidation)

— Automatically sync your API modules, endpoints, Docker topology, SQL queries, permissions, and Swagger spec into a beautiful interactive HTML dashboard.

Install complete Claude Code infrastructure in 30 seconds with automatic framework detection and skill auto-activation.

A memory-first AI agent that remembers why decisions were made — not just the last message. Runs local (Ollama), cloud (Claude · OpenAI · Gemini), or decentralized TEE.