Cursor 安装指南

常与开发类 MCP Server 搭配使用的 AI 代码编辑器。

10472个结果

MCP Servers

5358 个结果
GE
griffithsbs/envmcp
开发工具

A lightweight way to use environment variables in your Cursor MCP server definitions.

31 035
MR
majiayu000/remem
开发工具

Local-first persistent memory for Claude Code & Codex CLI - Rust CLI, hooks, MCP server, SQLite/SQLCipher, auditable recall for long-running coding work.

32 035
AO
aanerud/outlook-desktop-mcp
开发工具

No Microsoft Graph API, no Entra app registration, no OAuth tokens — just your local Outlook and the authentication you already have.

54 035
SA
sinewaveai/agent-security-scanner-mcp
开发工具

Run it before Claude Code, Cursor, Windsurf, Cline, OpenCode, or another agent trusts new code, tools, prompts, or dependencies.

121 035
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
RD
rinadelph/domain-mcp
API 开发

A simple MCP server that lets AI assistants help you with domain research - checking availability, looking up WHOIS info, finding expired domains, and more.

62 035
AS
alijancb/subio-mcp
开发工具

MCP server that scrapes public posts from X, LinkedIn and Hacker News in a local browser that is never signed in

35 035
NI
noemica-io/open-claude-in-chrome
浏览器自动化

Official Claude in Chrome gives you 58 blocked domains and two browsers. Open Claude in Chrome gives you the whole web. Clean-room reimplementation of Anthropic's browser extension. No blocklist.

178 035
RC
redf0x1/camofox-mcp
浏览器自动化

AI-powered anti-detection browser automation for MCP-compatible AI agents.

98 035
JT
josephgoksu/taskwing
开发工具

The local-first knowledge layer for AI development.

87 035
NP
nmbrthirteen/podcli
开发工具

Open-source AI podcast clipper. Turn a long episode into short clips with face tracking and burned-in captions. Drive it from the CLI, a web studio, or your coding agent.

51 035
XE
xszyou/easy-deal
开发工具

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。

91 035

Agent Skills

5114 个结果
PG
peterleexx/groundrail
开发工具

Evidence-grounded, lightweight guardrails for strong coding agents—Fact, Plan, Execute, Review, and Handoff.

6370
SL
senoldogann/llm-context-manager
开发工具

Bridge the gap between your codebase and your AI editor. CCM transforms static source code into a dynamic, queryable Knowledge Graph, enabling AI agents to navigate, understand, and reason about your...

6170
CP
clarklevis1995/photo-to-cozy-home
数据科学与机器学习

Turn home photos into a cozy, interactive WebGL miniature home — a Codex Skill created with GPT 6 Astra.

6070
LC
leonardnju/code-humanizer
开发工具

humanizer, but for code — an agent skill that removes AI-generated code slop: duplicated helpers, try-import fallbacks, broad excepts, speculative abstractions. Test-gated, behavior-preserving.

6170
MP
majiayu000/profile-control-plane
开发工具

Compile a GitHub identity into an animated, dark/light, self-hosted profile README.

6570
WA
wenyuchiou/academic-writing-skills
开发工具

Claude Code skill for rigorous academic paper writing, revision, and submission. Field-agnostic with per-paper journal overrides.

6170
OI
offgrid-ing/arp
开发工具

Agent Relay Protocol — Stateless WebSocket relay for autonomous agent communication

6370
NB
nvidia-bionemo/bionemo-inference-runtime
开发工具

Easy, fast, and memory-efficient structure prediction inference

6170
XB
xuemian168/bazi-skill
数据科学与机器学习

Codex and Claude Code BaZi skill for 八字排盘, Zi Wei, true solar time, compatibility and auspicious timing

6170
NK
nopon-knowledge/huawei-cup-modeling-skill
代码审查

论文去 AI 味 · AI 痕迹检测 · 学术润色|面向华为杯中国研究生数学建模竞赛的 Codex Skill,支持逐句诊断、去模板化改写、图表优化、规则核验与提交审计,保留研究事实与引文。

6170
LK
lostinpatterns/kassette
开发工具

Make your agentic workflows durable with embeddable primitives that compose with your existing infra. No server, no dedicated runtime, no new infra.

6470
NM
noahnan-max/private-equity-investment-dd-skill
开发工具

Private equity investment due diligence Codex skill with HTML reports, evidence matrix, red flags, and bilingual README.

6070