Cursor 安装指南

常与开发类 MCP Server 搭配使用的 AI 代码编辑器。

11766个结果

MCP Servers

5533 个结果
AA
ada20204/antigravity-sync-mcp
开发工具

⚠️ :此项目完全是 vibe coding 产物,代码由 AI 生成,未经严格审查。使用风险自己承担。

53 035
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
AM
aiagenta2z/mcp-marketplace
开发工具

Visit the website MCP Tool Use Agent App to explore MCP Servers with sota agentic AI Search/Deep Research, Finance Data,Chart Creation, Excel Spreadsheet/Powerpoint usage.

32 035
CC
capetlevrai/clipboard-vision-mcp
开发工具

Add vision to text-only models in Opencode (, ) — , no manual file saving.

44 035
MM
markifact/markifact-mcp
开发工具

MCP server for Google Ads, Meta Ads, GA4, TikTok Ads, and LinkedIn Ads. Manage 300+ ad operations from Claude, ChatGPT, Gemini, Cursor, or any AI client. Human-in-the-loop on every write.

48 035
CL
ces-ltd/lumi
开发工具

Unified native desktop UI for Claude Code, Gemini CLI, Hermes, Crush, Codex, and Cursor — multi-agent, MCP-native, written in Rust + GPUI.

33 035
AF
ashwwwin/furi
开发工具

furi is an easy to use, CLI & API for MCP management.

172 035
LM
lydakis/mcpx
开发工具

Tool names match exactly what each server exposes. Tool-call output passes through unchanged (text or JSON), so you can pipe, redirect, or parse with jq.

52 035
AM
arc-mcp/arc-1
开发工具

(pronounced arc one [ɑːrk wʌn]) — Enterprise-ready MCP server for SAP ABAP systems. Secure by default, deployable to BTP or on-premise, and hardened with large unit/integration/E2E test coverage.

158 035
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
FC
florianbruniaux/ccboard
分析与监控

combining Claude Code monitoring, Claude Code config management, hooks, agents, and MCP servers in a single 5.8MB binary. 89x faster startup with SQLite cache, 492 tests, 0 clippy warnings.

90 035
FM
fjwood69/mori
开发工具

mori MCP server — a governed memory layer for AI coding agents.

30 035

Agent Skills

6233 个结果
BS
base/skills
开发工具

Agent Skills for building on Base. These skills enable AI agents to connect to Base, deploy contracts, integrate wallets, run nodes, and more.

10470
IS
innei/skill
开发工具

This repository stores personal Codex / Claude Code skills in a scalable directory layout.

6070
SA
slowlyc/agent-gpu-skills
开发工具

GPU 开发 Agent Skill 集合,适用于 Cursor / Claude Code / Codex / Gemini CLI。

15070
AR
ai4s-research/ai4s-skills
开发工具

Seven agent skills for AI-for-Science research — turn a research direction into literature surveys, runnable experiments, publication-grade papers, and integrity audits, with every citation, number,...

15670
LS
labrai/skillcenter
开发工具

Every agent skill on GitHub — in one install.

9170
QD
qinghonglin/data2story-skill
开发工具

A data-journalist agent skill that turns any dataset into a verifiable, evidence-grounded multimodal story — a self-contained HTML article where every sentence traces back to the data or source that...

14770
MP
moshuying/pitchcraft
开发工具

A Claude Agent Skill for structured persuasion—

18270
FS
frappe/skills
开发工具

A collection of agent skills for building Frappe Framework applications, plus general code-style and UI design skills.

8170
ED
ertugrul-dmr/clean-code-skills
开发工具

This repository contains Agent Skills that enforce Robert C. Martin's Clean Code principles. They work with Google Antigravity, Anthropic's Claude Code, and any agent that supports the Agent Skills...

14070
MS
mmlong818/skillforge
开发工具

SkillForge 是一个完整的 Web 应用,内置经过实战验证的 ,严格对齐 Anthropic 官方 Agent Skills 规范。

8670
DT
dotanminh/travel-optimization-engine
开发工具

Bộ 8 AI Skills tự động hóa toàn bộ quy trình tối ưu chi phí vé máy bay. Tiết kiệm 30-66% cho cá nhân/gia đình, 10-15% cho doanh nghiệp.

3870
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