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

A self-modifying, self-verifying AI agent with persistent state. Reads its own source code. Plans changes. Tests them in a sandbox before applying.

makes it easy to deploy and serve Haystack Pipelines and Agents.

(pronounced arc one [ɑːrk wʌn]) — Enterprise-ready MCP server for SAP ABAP systems. Secure by default, deployable to BTP or on-premise, and hardened with large unit/integration/E2E test coverage.

Deploy anything on your own servers. Connect a server, click deploy, done. MIT licensed and free to self-host forever.

Self-hosted audit trail for AI agents — one command or one dashboard click from any step back to root cause.

Hosted uptime monitoring and public status pages for teams. Multi-region checks, automatic incidents, on-call alerts (Slack/Telegram/webhook/+), subscribers, REST API, Terraform provider, MCP server.

AgentStack is a production-grade multi-agent framework built on Mastra, delivering 50+ enterprise tools, 25+ specialized agents, and A2A/MCP orchestration for scalable AI systems.

Keep Claude Code context clean. Open-source toolkit: drift detection, re-read dedup, integrity scoring, AST-aware reads, 15 MCP tools. 62.6% measured savings, reproducible.

Local RAG layer and optimizer for your Markdown knowledge base. CLI + MCP server: grounded answers for any AI client, stale-note detection, session harvesting into memories. Local-first.

Find local coding-agent sessions and copy their user and assistant messages into another agent's native format. TUI, CLI and MCP.

A local-first Playwright test automation toolkit for AI coding agents (Cursor, Claude Code, Copilot), with MCP tools for codegen, browser control, and recordings.

GCO is a platform that spins up EKS Auto Mode clusters across AWS regions, wired together with Global Accelerator for low-latency routing.
Agent Skills

A CLI for Bilibili — browse videos, users, favorites from the terminal 📺

仓库根目录的 是通用蒸馏引擎。下面三套是独立仓库的扩展 Skill——蒸馏、保护、授权,一条龙。 :先看 (四段可复制指令)。

a desktop app for getting work done with any model

an autonomous AI agent: you describe the thing, it does the thing.

Every AI agent needs a loyal companion. Meet Pup — the CLI that gives your agents full access to Datadog's observability platform (because even autonomous agents need good tooling, not just tricks).

Provider-neutral Codex Skill for producing verified AI presenter videos from a script and an authorized presenter image.

一个轻量的 :通过 Chrome DevTools Protocol 连接本地已登录的 Chrome,复用真实登录态调用 zhipin.com 搜索 API,绕过前端字体反爬,输出含**的职位数据(JSON / CSV),并生成薪资分布、技能词频和求职材料优化提示词。同时作为 Hermes Agent Skill 提供。

Official Agent skills of Oxylabs products

这是 codex-windows-fast-patch skill 的公开版本,用于让支持 Agent Skills 的智能体修复 Windows 版 Codex Desktop 更新后常见的功能失效问题。

Fetch WeChat Official Account articles and convert them to clean Markdown.

你只想说一句“帮我做个 App”,但 Codex 真正需要的是一个能执行、能验证、知道边界、知道何时停下来的目标。 qiaomu-goal-meta-skill turns vague work into a copy-ready Codex /goal command with defaults, verification, boundaries, and pause conditions.

You wrote a good SKILL.md. But did the agent actually follow it, or skip the late safety rule, grab an undeclared tool, and report "done" with no proof?