Cursor 安装指南

常与开发类 MCP Server 搭配使用的 AI 代码编辑器。

10039个结果

MCP Servers

5255 个结果
YP
yiwenlu66/piloty
开发工具

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

44 035
JR
joshuaswarren/remnic
开发工具

Open-source, local-first memory and context for AI agents. One memory store, every agent.

162 035
SA
ssdeanx/agentstack
开发工具

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.

44 035
HF
hagaihen/facebook-mcp-server
开发工具

This project is a for automating and managing interactions on a Facebook Page using the Facebook Graph API.

184 035
SC
scottweiss/claude-codex-mcp-starter
开发工具

A starting point for Claude Code to Codex collaboration

38 035
DG
data-goblin/learn-mcp-servers
分析与监控

The purpose of the repo is to teach you how to make MCP servers. The target audience are non-technical with no real coding experience.

52 035
AR
agentic-research/mache
开发工具

IDE-style navigation for structured data — code, JSON, YAML. Jump to definitions, find callers, follow references. Available as an MCP server or a mounted folder.

45 035
ED
elliot35/deterministic-agent-control-protocol
开发工具

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

90 035
RN
raphasouthall/neurostack
开发工具

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.

47 035
NN
nitrocloudofficial/nitrostack
开发工具

The enterprise-grade TypeScript framework for building production-ready MCP servers. Decorators. Dependency Injection. Widgets. One framework to ship AI-native backends.

2024 035
AM
aiagenta2z/mcp-marketplace
开发工具

Visit the website MCP Tool Use Agent App to explore MCP Servers with sota agentic AI Search/Deep Research, Finance Data,Chart Creation, Excel Spreadsheet/Powerpoint usage.

32 035
MC
mlobo2012/claude_desktop_api_use_via_mcp
开发工具

MCP server implementation for using Claude API with Claude Desktop, providing advanced API integration and conversation management.

34 035

Agent Skills

4784 个结果
IS
inhouseseo/superseo-skills
开发工具

No exports. No API keys. No paste-in data. Production-tested at InhouseSEO.

24841
AR
alfonso0512/research-writing-skill
代码审查

🎓 基于 AI 的科研论文写作助手,提供 30 个 Prompt 模板覆盖论文写作全流程 : 3.0 | : MIT | : 中文/英文

36341
DS
dylantmoore/stata-skill
代码审查

This project contains two Claude Code skills:

27041
OF
ognjengt/founder-skills
开发工具

This repository contains 20+ Claude skills that will help you turn Claude into a Fortune 500 growth team.

25841
NA
nicepkg/ai-workflow
开发工具

One command. 170+ professional skills. Instant productivity boost.

27641
MH
mit-han-lab/kernelwiki
开发工具

This skill is maintained as a standalone submodule of Kernel Design Agents (KDA) for easy installation.

31041
CA
credittone/android-reverse-engineering-skill
开发工具

Android 逆向分析全家桶 — 从 APK 反编译到 Frida 动态插桩、从 HTTP 接口提取到 JNI/SO 原生层逆向,覆盖静态分析→动态分析→流量解密→签名追踪的完整链路。支持 Claude Code / Codex 双平台,兼容 macOS、Linux、Windows(PowerShell),一套技能打通 Android 安全研究与授权渗透测试的绝大部分需求。

35841
CA
chjm-ai/stock-daily-analysis-skill
代码审查

基于 LLM 的股票智能分析 Skill,为 OpenClaw 提供 A股/港股/美股 技术面分析和 AI 决策建议。

23041
IA
iart-ai/motion-skills
开发工具

— kinetic typography, data-driven charts, explainers, TikTok / Reels, 3D & WebGL, math animation, generative illustration, and web motion. Fifteen installable packs.

34041
GD
ginobefun/deep-reading-analyst-skill
开发工具

A professional Claude AI skill that transforms surface-level reading into deep learning through systematic analysis using proven thinking frameworks.

34541
JQ
joeseesun/qiaomu-cut-skill
开发工具

你只说一句“我要什么视频”,它把素材、分镜、字幕、转场、动效、渲染和质检组织成一个可复现的视频工程。 Say what video you want; qiaomu-cut turns it into a source-aware, renderer-ready, verifiable video project.

31041
FP
fcakyon/phd-skills
分析与监控

Catch AI mistakes before they cost weeks of compute. Reproduce papers from arxiv. Debug runs evidence-first. Compare experiments at the right epoch. Launch with discipline.

36141