Cursor 安装指南

常与开发类 MCP Server 搭配使用的 AI 代码编辑器。

11147个结果

MCP Servers

5414 个结果
AZ
aptro/zerodha-mcp
开发工具

This project integrates Zerodha's trading platform with Claude AI using the Multi-Cloud Plugin (MCP) framework, allowing you to interact with your Zerodha trading account directly through Claude.

46 035
JT
josephgoksu/taskwing
开发工具

The local-first knowledge layer for AI development.

87 035
GM
g12789/mcp-quickstart
API 开发

One command. TypeScript Python. Example tools, the Inspector, and tests — all wired up. Or point it at an OpenAPI spec and get

82 035
YI
ychangqing/igraph
开发工具

IGraph 把代码仓库解析为「符号节点 + 调用关系边」的知识图谱,叠加 LLM 语义摘要与向量索引,通过双通道(Dense + FTS5)RRF 融合检索对外服务。支持挂载 PRD / DB Schema 等多模态资源建立跨模态关联,内置 MCP Server 可直接接入 Cursor / Claude Code 等 AI 助手。

52 035
ES
eversmile12/sharedcontext
开发工具

Sovereign, encrypted, portable memory for AI agents.

50 035
RA
recallium-ai/recallium
开发工具

Your digital developer twin — because "explain our setup again" gets old fast.

50 035
CT
czarnak/tia-portal-mcp
开发工具

Specialized bridge designed to connect LLMs and AI agents directly to Siemens SIMATIC TIA Portal V21.

45 035
CM
clerk/mcp-tools
开发工具

A library built on top of the MCP TypeScript SDK that makes it easier to implement MCP with auth into your MCP client and/or server.

47 035
PM
portswigger/mcp-proxy
开发工具

A Stdio MCP server which proxies an SSE MCP server.

34 035
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
CM
chatmcp/mcpso
开发工具

directory for Awesome MCP Servers

2023 035
AO
alterhq/openpets
开发工具

OpenPets is a native macOS desktop pet for visible agent progress, review prompts, completion states, and lightweight animations across local coding tools.

89 035

Agent Skills

5733 个结果
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
EA
epoko77-ai/design-diversity
数据科学与机器学习

AI에게 PPT·웹사이트를 맡기면 결과물이 늘 비슷합니다. **을 설치하면, 서로 뚜렷이 구별되는 중 하나를 골라 Claude가 그 스타일대로 만들어 줍니다.

17740
BN
bayramannakov/notebooklm-youtube-skill
开发工具

A Claude skill that automates NotebookLM notebook creation from YouTube videos — research featured people, add sources, and generate Audio Overviews automatically

7540
6D
6mikao9/dsh-wsl-workspace
开发工具

WSL workspace support for DeepSeek Harness——无缝的 WSL 工作区使用体验,无需在 WSL 之中再安装一个dsh,安装该插件后在 GUI 里直接添加 WSL 工作区即可。

5140
AS
alchaincyf/sun-yuchen-perspective
开发工具

基于6个维度(著作、深度采访、表达DNA、他者视角、决策记录、时间线) 共1528行调研素材的深度蒸馏, 提炼6个核心心智模型、8条决策启发式、5种割味造句公式。

17740
CD
cdespace/detection-skills
代码审查

The entire knowledge around the detection lifecycle, encoded into skills. More details at https://detectionskills.io/

5340
SC
sebastiendegodez/copilot-instructions
开发工具

Welcome to the repository! This project provides a set of best practices, coding rules, and prompt instructions to guide AI-assisted development, especially with GitHub Copilot and similar tools.

19240
MV
microsoft/vscode-chat-customizations-evaluation
开发工具

An extension for analyzing and improving AI prompt files. Works with SKILL.md, .agent.md, .instructions.md, and .prompt.md files — providing LLM-powered semantic analysis directly in VS Code.

13440
MI
mohamedameen-io/startupkit
开发工具

StartupKit is an for Claude Code. It decomposes the business-ideation problem into a bounded sequence of 11 phases — diverge → niche → competitors → positioning → offer → validate → money → leads →...

15840
SG
sawyerhood/glyphdown
开发工具

Google Docs for markdown files — real-time multiplayer editing, comments, suggestion mode, edit history, and a CLI built for AI agents.

5440
AC
aiskilloftheweek/claude-ai-skill-of-the-week
开发工具

Curating the greatest Claude AI Skills that actually change how you work.

11840
DD
dazhuangjammy/dazhuangskill-creator
开发工具

基于 Claude Code 官方 skill-creator,我融入了自己对提示词架构、Skill 架构以及 CLI 工具运行机制的理解,对其进行了全面重构,打造了一个新版 Skill Creator。 在测评环节,我采用 Codex 的 Headless 模式(无需打开图形界面,直接在终端执行)进行了三轮以上的独立对话测试。测试结果显示,新版在各项维度上全面超越原版。

5340