Cursor 安装指南

常与开发类 MCP Server 搭配使用的 AI 代码编辑器。

10818个结果

MCP Servers

5385 个结果
MD
mrmartinimo/docmost-mcp
开发工具

A Model Context Protocol (MCP) server for Docmost, allowing AI agents to manage documentation spaces and pages.

30 090
LF
laurigates/foundryvtt-mcp
开发工具

A Model Context Protocol (MCP) server that integrates with FoundryVTT, allowing AI assistants to interact with your tabletop gaming sessions.

31 090
IX
ino-xious/stockbit-mcp
开发工具

Model Context Protocol (MCP) server for Stockbit (Indonesian / IDX market) — broker summary / bandarmology, quotes, top movers, orderbook, fundamentals, sentiment, your portfolio, and your real...

38 090
LO
lemaiwo/odata-mcp-proxy
开发工具

A config-driven MCP (Model Context Protocol) server that exposes OData and REST APIs as MCP tools. This enables AI assistants such as Claude to query, manage, and monitor SAP backends through natural...

30 090
FW
felixisaac/whatsapp-mcp-extended
开发工具

Actively maintained WhatsApp MCP — 26 tools, webhooks, anti-ban, Docker, self-healing. Drop-in for abandoned lharries/whatsapp-mcp.

31 090
KM
kts982/mcp-sap-gui
开发工具

MCP server for SAP GUI for Windows automation via the SAP GUI Scripting API.

33 090
JD
jmtanguy/droit-francais-mcp
开发工具

Serveur MCP pour des recherches directement sur Légifrance et Judilibre.

32 090
AG
akxan/google-seo-mcp
开发工具

SEO & GEO MCP server for Claude, Codex, Cursor and any MCP client: Search Console, GA4, PageSpeed, Core Web Vitals, structured data, llms.

36 090
IM
ilyautov/marketplaces-mcp-ru
API 开发

MCP-сервер для кабинетов Wildberries, Ozon, Яндекс Маркета и Авито: продажи, заказы, остатки, цены, финансы, отзывы через API напрямую, без браузера. 1022 метода schema-driven, safety-гейт на запись.

30 090
AA
axiommath/axle-mcp-server
开发工具

MCP Server for AI agents to interact with our Lean infrastructure

37 090
BI
bcharleson/instantly-cli
开发工具

CLI and MCP server for the Instantly.ai cold email platform

36 090
DN
dondetir/neuralbridge_mcp
开发工具

🧠 AI-native Android automation via MCP. Give Claude, GPT, Gemini or any AI agent full control over Android — tap, swipe, type, screenshot — with ~6ms latency. 100x faster than Appium. 43 tools.

30 090

Agent Skills

5433 个结果
HS
hanamizuki/solopreneur
开发工具

is a family of Claude Code and Codex plugins that gives solo founders the workflows of a full engineering org: plan review, code review loops, automated PR cycles, marketing, design, and...

14340
IS
iammm0/secbot
开发工具

Authorized security testing workspace. v2 TypeScript terminal product on release; v1 Python on pypi-release; Go branch is demo only.

7440
DL
devcodex-labs/devcodex
开发工具

识别意图 · 读取项目 · 调用专业 Skill · 确认边界 · 自动推进 · 执行修改 · 验证结果 · 保存进度 · 跨会话续接 · 受控进化

9140
CT
codeswithroh/tastemaker
开发工具

A skill that gives AI real design taste, so the UI it builds does not look AI-generated.

11940
ST
stanleychanh/tushare-finance-skill-for-claude-code
开发工具

专为 Claude Code 设计的 Tushare Pro 金融数据技能包,支持 220+ 个接口,用自然语言获取 A 股行情、财务数据、宏观经济等金融数据。

7840
1B
199-biotechnologies/motion-dev-animations-skill
写作

A Claude Code skill that generates 120fps GPU-accelerated animations using Motion.dev (the successor to Framer Motion).

9040
AW
amap-web/amap-skills
开发工具

is a set of AI programming skill packages designed specifically for AI IDEs. It integrates the official documentation, best practices, and code templates of AMap JavaScript API v2.

15940
AD
aipmandy/dna-memory
开发工具

DNA Memory 把一个 Markdown/Obsidian 目录作为长期记忆真源,把 SQLite 作为可删除、可重建的索引。多个 AI 客户端通过同一个 MCP 服务召回、写入和反馈, 不再各自维护互相冲突的长期记忆副本。

9240
S1
steelmorgan/1c-agent-based-dev-framework
开发工具

Фреймворк агентной разработки для 1С BSL с применением модульного подхода. Позволяет настроить AI-агентов (Cursor, Claude Code и др.

9040
HA
huangbai-ai/sd-2-5-prompt
数据科学与机器学习

SD 2.5 Prompt 是一套面向 Seedance 2.5 / SD 2.5 视频生成的实用 Skill。它不依赖冗长术语,用五个部分统一处理产品广告、人物动作、原片反推、多模态参考、音乐节奏和复杂打斗。

9240
TO
turmyshevd/openclawgotchi
开发工具

(▰˘◡˘▰) - AI Tamagotchi on Raspberry Pi. Agentic life-form with an E-Ink face

5040
GE
gadievron/exploitation-validator
开发工具

A prompt-based pipeline for finding, validating, and proving vulnerabilities using LLM sub-agents — structured to resist false positives.

9440