Cursor Install Guide
AI code editor frequently used with developer-focused MCP servers.
MCP Servers

Drop a .pcap file, ask questions in plain English — get answers backed by real tshark data.

PiloTY: AI pilot for PTY operations via MCP - enables AI agents to control interactive terminals like a human

MCP server to enable an LLM to do basic static triage of a PE.

Intercept AI requests, track usage, inject MCP tools centrally

🔥 MCP Mastery: Build AI Apps with Claude, LangChain and Ollama

is the easiest way to connect any MCP client (like Claude or Cursor) with the browser using browser-use.
Agent Skills

规则和模板基于 (国赛一等 + 美赛 O/F 奖,2018-2025)的系统分析提炼。

Note Slides Skill 是一个把访谈、播客、公众号长文、课程稿和复盘材料整理成 HTML 版本笔记幻灯片的 Skill。

A C++ WebView UI Library. Nui enables you to build C++ user interfaces using a browser window tied to a main process.

An autonomous, looping, multi-altitude for a codebase, packaged as a Claude Code . It replaces the model's default "single pass, summarize, stop" behaviour with an explicit search procedure: traverse...

Gemini CLI will be replaced by Antigravity CLI on June 18th. If you previously installed oh-my-gemini-cli in Gemini CLI, Antigravity CLI will ask whether to import plugins during installation.

A Claude Code / OpenClaw skill and component library for building web interfaces with the aesthetic — the visual identity of a fictional military-scientific organization from Neon Genesis Evangelion.

A curated collection of real-world use cases, workflows, and creative scenarios — contributed by the community.

A Godot editor plugin that lets you remotely execute arbitrary GDScript code snippets via an HTTP API.

AI Partner Chat 通过整合用户画像、AI 画像和向量化的个人笔记,提供个性化的、上下文感知的对话体验。这个技能让 AI 能够记住并引用你之前的想法、偏好和知识库,创造出更加连贯和个性化的交互体验。

让 AI 不只会“看网页、回答问题”,还能够安全地完成研究、比较、填表和后台操作等多步骤网页任务。

A minimal, working multi-model team for opencode: a that plans and reviews but , delegating every change to a cheaper, faster . Inspired by the Devin Fusion "sidekick" pattern from Cognition.

The spec-driven development system where specs and tasks live in your repo and never drift from the code.