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
SC
shixinnt/codex-image-context-runtime
开发工具

Fictional concept interface—not an actual Codex UI or a measured context, token, speed, or latency benchmark.

100 035
AD
aviveldan/datagov-mcp
开发工具

An MCP server for exploring Israeli government open data (data.gov.il) — with built-in interactive visualizations powered by MCP Apps.

145 035
XH
xaaha/hulak
开发工具

Git-native API client with encrypted secrets.

90 035
SB
sandraschi/blender-mcp
开发工具

Headless Blender automation via FastMCP — 41 portmanteau tools (150+ ops). Batch mesh/VSE/Grease Pencil, VRM, Gaussian splats; optional live bridge. For Cursor / Claude Desktop.

38 035
FF
forward-future/deploybot
开发工具

Agent-managed GitHub merge queue for Codex, Claude Code, Cursor, and MCP clients

45 035
CY
code-yeongyu/perplexity-advanced-mcp
开发工具

Perplexity Advanced MCP is an advanced integration package that leverages the OpenRouter and Perplexity APIs to provide enhanced query processing capabilities.

49 035
MC
moonlin1213/cove-sensory-mcp
开发工具

is a local stdio MCP server that lets an Agent ask configured multimodal providers to inspect an explicitly supplied image, video, audio file, or music file.

60 035
HT
healthymind-tech/taiwan-health-mcp
开发工具

台灣醫療健康資料整合 MCP 伺服器 整合 ICD-10-CM/PCS、SNOMED CT、LOINC、台灣 FDA 藥品 / 健康補充品 / 食品營養,以及 FHIR R4 IG 授權與驗證工具

159 035
WM
wide-moat/open-computer-use
开发工具

MCP server that gives any LLM its own computer — managed Docker workspaces with live browser, terminal, code execution, document skills, and autonomous sub-agents.

115 035
XA
xpack-ai/xpack-mcp-marketplace
开发工具

English Français Deutsch Español 日本語 한국어 繁體中文 简体中文

169 035
AS
ahucodingbeast/spring-ai-mcp-demo
开发工具

SpringAI和SpringAI-alibaba都发布了最新依赖稳定版本(之前基于快照版本需要设置Repository 如今已经不需要设置),如果遇到依赖下载不下来请按照最新的官方文档修改依赖版本,官网快照版本更新很快可能出现API冲突的情况 请以最新版本的API设计为准 推荐参考文档:https://java2ai.com/docs/1.0.0.

66 035

Agent Skills

4784 个结果
SO
smartfrog/opencode-froggy
开发工具

OpenCode plugin providing hooks, specialized agents (architect, doc-writer, rubber-duck, partner, code-reviewer, code-simplifier), skills (ask-questions-if-underspecified, tdd), and tools (gitingest,...

10555
RF
ricardonevesbraga/flowgrammers-skills
分析与监控

Contexto 100% brasileiro · Multi-plataforma · Claude Code, Cursor, Codex, Windsurf, OpenClaw

10355
AW
appleweiping/weiping_wiki
开发工具

A source-backed knowledge system for turning research, conversations, and agent work into maintained, interlinked Markdown.

12355
WA
weijt606/anti-vibe-writing
开发工具

An agent writing skill that removes the AI-generated feel from documents. Works in English and Chinese, with optional modes for matching a specific author's voice.

10955
GQ
genjiyin/quantmanus
开发工具

QuantManus 是一个基于大语言模型(LLM)的智能 Agent 框架,专注于**、**和**。

8855
LM
l3gi0nxxxx/metis-agent
开发工具

Metis is a high performance and personal AI assistant which is build with Cangjie program language. And this project is based on magic-cli and CangjeMagic.

12855
CP
ciao1019/petrichor
开发工具

An open-source full-stack knowledge base & blog platform built with Next.js, Supabase and Vercel.

10855
AQ
andrewstellman/quality-playbook
开发工具

Most code review looks at how the code is written. The Quality Playbook looks at what the code is supposed to do, and whether it actually does it.

8255
JO
josipjelic/orchestrated-project-template
部署与 DevOps

A bootstrapping template for software projects built with Claude Code. Use it as a GitHub template, run , and Claude walks you through setting up all the documentation before a single line of code is...

9455
EN
equinor/neqsim
开发工具

From Simulation Models to AI-Assisted Industrial Workflows

14055
UP
useai-pro/openclaw-skills-security
开发工具

Curated, security-first OpenClaw skills (Markdown-based). Security audit skills - detect prompt injection, supply chain attacks, credential leaks. Works with Codex CLI, Claude Code, any LLM.

7255
NE
namuh-eng/ralph-to-ralph
开发工具

A three-phase autonomous pipeline that inspects any SaaS product, builds a working clone with real cloud infrastructure, and QA-tests everything — no human in the loop.

10255