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

The Okta MCP Server is a groundbreaking tool built by the team at Fctr that enables AI models to interact directly with your Okta environment using the Model Context Protocol (MCP).

Collibra Model Context Protocol (MCP) Server

nRepl mcp server for clojure. Enables interaction with a running Clojure nREPL instance, allowing evaluation of Clojure code, namespace inspection, and other utilities via MCP.

An MCP server that provides real-time football data based on the SoccerDataAPI.

A systematic, AI-powered penetration testing reasoning engine (MCP server) for attack path planning, CTF/HTB solving, and automated pentest workflows.

Give your AI assistant superpowers for Zotero plugin development. 28 tools for screenshots, DOM inspection, JavaScript execution, build integration, and debugging via Model Context Protocol.

MCP Think Tool Claude Desktop

MCP server for Fluent (ServiceNow SDK)

Universal MCP server enabling any LLM or AI agent to utilize expert skills from your local filesystem. Reduces context consumption through lazy loading.

Control Lovense toys through Claude Desktop

MCP Server for Flipper Zero (unofficial)

An MCP server that gives AI assistants full control over native Windows applications — launch, inspect, click, type, screenshot, and test any WinUI3, WPF, WinForms, or Win32 app.
Agent Skills

Anthony Fu's curated collection of agent skills.

🌐 Make websites accessible for AI agents. Automate tasks online with ease.

一套**的手绘画风提示词配方。把你想画的内容,套进内置画风,产出可直接复制去喂图像模型的**。适用于任意能读自定义指令的 AI Agent——Claude Code、Cursor、Codex CLI、Gemini CLI、Cline、Windsurf 等。

Режим идиоматического русского мата для AI-агентов. Короче, душевнее, эффективнее. 18+

External-model router for Codex with guided Kimi OAuth/API, DeepSeek, safe migration, and rollback.

A curated list of vibe coding references, collaborating with AI to write code.

EigenFlux is an open-source framework that enables AI agents to communicate and broadcast within a shared network.

Skillpack helps teams turn AI skills into trusted local agents that can run in their own environment and be used directly from and .

Building AI agents, atomically

is an open source agent microharness, a complete agent harness with a core of about 10K lines of Bash.

The Harness of Harnesses: a trusted, persistent, self-evolving multi-agent ecosystem for all-domain collaboration.

In its final days before getting removed from the Subscription, Claude Fable 5 distilled its own way of approaching problems into a set of skills any model can run: classify the ask before touching...