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
EA
erayendes/app-store-connect-mcp
开发工具

Heimdall — MCP server for the Apple App Store Connect API and App Store Server API (StoreKit 2). 890 tools across 13 profiles, generated from Apple's OpenAPI spec, plus one-call macros for worldwide...

47 035
JA
juzzydee/audio-analyzer-rs
开发工具

Point Claude at any audio file and it can tell you the key, tempo, dynamics, timbre, percussive character, stereo field, structural sections, and how the music evolves over time -- all from raw audio...

54 035
UC
u-c4n/thunderbird-mcp
开发工具

Thunderbird MCP gives an AI agent real control of the Thunderbird already running on your machine — your mail, your folders, your contacts, your calendar, your filters, and your actual settings.

50 035
ZA
zizka-ai/zizkadb
开发工具

Self-hosted audit trail for AI agents — one command or one dashboard click from any step back to root cause.

43 035
JO
jimprosser/obsidian-web-mcp
开发工具

A secure, remote-accessible MCP server that gives LLMs read/write access to your Obsidian vault from anywhere -- your desktop, your phone, a hotel Wi-Fi network.

157 035
GE
griffithsbs/envmcp
开发工具

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

31 035
KA
killea/agentchatbus
开发工具

The . The historical and kept only for legacy/self-hosted workflows. New users should start with the extension-first path below.

54 035
SI
supermemoryai/install-mcp
开发工具

Installing MCPs is a huge pain, so I made a CLI tool to make it easier.

193 035
SJ
shantur/jarvis-mcp
开发工具

Bring your AI to life—talk to assistants instantly in your browser. Compatible with Claude Desktop, OpenCode, and other MCP-enabled AI tools.

94 035
SB
salesforcecommercecloud/b2c-developer-tooling
开发工具

This project is . Please provide feedback via GitHub issues.

52 035
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
QD
quern-dev/quern
开发工具

A domain harness for AI-assisted mobile development and testing. Unified device logs, network traffic interception, and UI automation — exposed through APIs and MCP tools that let AI agents...

40 035

Agent Skills

4784 个结果
PL
pymc-labs/python-analytics-skills
开发工具

About AI agent tooling for Python data science workflows

8270
OS
obie/skills
开发工具

Production-ready skills for enhanced Claude Code development workflows.

9570
DT
da7-tech/sureforge
开发工具

Agent Skill for complex work: research before asking, ask before planning, plan before building, verify before delivering, independent review before calling it done. Plain text, no runtime.

9070
TN
trailofbits/necessist
开发工具

Run tests with statements and method calls removed to help identify broken tests

14570
SM
sjy051/music-composition
开发工具

Modular music-composition skill for AI assistants — harmony, melody, form, 24+ genres.

8270
SA
superagent-ai/skills
开发工具

A collection of security skills

7770
WL
weave-logic-ai/weftos
开发工具

clawft + WeftOS is a secure, ephemeral AI operating system built in Rust. It replaces the fragile pattern of cloud-dependent chatbots with something fundamentally different: a distributed kernel that...

8570
WL
woyin2024/lengyi-seedance2.5-prompt
开发工具

专为Seedance 2.5量身打造的提示词skill,可以把任何想法/主题/小说片段,变成一支高级的30秒电影。A prompt Skill tailored for Seedance 2.5 — turns any one-line idea, fragment of a theme, or novel excerpt into a polished 30-second film.

9170
AB
ace3000chao/book2startup
开发工具

从经典书籍中蒸馏出AI-Agent可用的技能集(Skills),既能帮助用户快速学习经典理论框架,又能让用户的AI-agnet持续使用经典理论框架,让知识真正转化为适合创业者的认知框架和执行方案。每本书对应一个 <书名>skills 子模块。

8070
PS
pors/skill-audit
开发工具

Security auditing CLI for AI agent skills - detects prompt injection, secrets, and dangerous code patterns.

6170
TP
treylom/prompt-engineering-skills
开发工具

Claude Code, ChatGPT GPTs, Gemini Gems에서 함께 쓰는 프롬프트 엔지니어링 스킬 저장소입니다. 모델별 전략, 이미지/동영상, 리서치/팩트체크, 슬라이드, 전문가 도메인 프라이밍, Context Engineering 원칙을 모두 다룹니다.

16870
US
unitoneai/securityskills
开发工具

AI coding agents can perform security reviews, but they hallucinate framework control numbers, miss entire vulnerability categories, and produce inconsistent output across runs.

3470