Cursor 설치 가이드
개발자용 MCP 서버와 함께 자주 쓰이는 AI 코드 에디터.
MCP Servers
一款面向 的跨平台桌面工具。把提示词模板、自定义 Prompt、第三方 API 供应商、会话同步、Skills / MCP 和 TOML 配置都放进可视化界面里，不用反复手改文件。
MCP server for interacting with Apache Superset, enabling AI agents to connect to and control a Superset instance programmatically.
makes it easy to deploy and serve Haystack Pipelines and Agents.
MCP server that scrapes public posts from X, LinkedIn and Hacker News in a local browser that is never signed in
MCP server that gives any LLM its own computer — managed Docker workspaces with live browser, terminal, code execution, document skills, and autonomous sub-agents.
AI-powered anti-detection browser automation for MCP-compatible AI agents.
Local-first creative studio with 37 model routes, transparent costs, local archives, and MCP access.
就算有一套完全自动赚钱的工具，你也会经常盯着它。你跟专业交易员对比，差别在于是否看得懂。而EasyDeal 就是解决这个问题的一套框架，提供一组MCP工具，接入 openclaw、Claude Code, Fay等agent后，在MT5交易环境可以协同各种策略工作，监控策略的执行、为你解答各种问题、指导你做出突发处理，甚至直接帮你修改策略代码。
A powerful Clojure-based MCP server built for querying DataScript and integrating with AI workflows.
开源 AI 低代码平台：.NET 10 + Vue 3 + Redis，以 V8 引擎连接 AI 编程、可视化建模与企业级交付。 支持 VS Code / Codex / Copilot / Cursor / Claude + MCP + Skills，本地或在线开发，保存即生效。
Overleaf CLI - pull, push, sync, compile LaTeX projects from your terminal. Git remote helper, MCP server for AI agents, and TypeScript library.
Desktop extension (.mcpb) for Claude Desktop. Single-click install via Settings → Extensions.
Agent Skills
A collection of practical skill plugins for AI coding agents.
前阳光私募冠军基金经理、B站百大UP主的交易纪律，封装成可运行在真实行情上的 AI Skill。 基于 ~200 万字语料蒸馏，60+ 指标，30+ 战法，可回测可模拟、可自改进、可走完整闭环。
Built from practice, not theory — calibrated against real deals including vLLM/Inferact ($150M @ $800M) and Hugging Face ($235M @ $4.5B).
面向硬件产品的PCB方案设计 AI Agent。输入产品需求，输出可评审、可落地的PCB原理图的方案。
Watchmen turns every coding session into the skill bundles you’d never sit down and write yourself.
A framework for AI-First development with Claude Code and Codex. One methodology, two compatible runtimes.
Code is cheap. Context, control, and evidence are not. Let the model move the work forward. Let the human own goals, boundaries, permissions, checkpoints, evidence, and acceptance.
终端里起多个会话并行干活、互相通信；长任务跑着的时候人走开了，也能从微信/企微把它喊回来。
Make AI coding agents remember your project between sessions.
A Claude Code skill for maintaining and optimizing OpenClaw workspace files — the markdown files that form an AI agent's soul, memory, and operating procedures.
A file-backed, spec-driven workflow for building real software with AI while staying in control.
A : type /codex-workflows and a fleet of fans out across the work — Claude authors the workflow, runs it on your local codex app-server, and streams it back as a live .