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
TM
tanigami/mcp-server-perplexity
开发工具

:warning: - The Claude Desktop client may timeout if Perplexity processing takes too long - This issue might be resolved if Claude Desktop implements support for long running operations and progress...

94 055
KP
koul777/public-regulation-mcp-builder
开发工具

v1.2.21에서는 독립 Qwen 챗봇이 기본적으로 빠른 승인 BM25/lexical 검색을 사용합니다. 질문을 보내면 검색·답변·인용 검증의 실제 진행률과 경과 시간이 계속 보이고, 승인·색인이 끝난 규정만 선택할 수 있습니다. MCP 생성·연결 경로와 기존 승인 데이터는 그대로 유지됩니다.

33 055
PV
pluginslab/vphone-mcp
开发工具

MCP server for programmatic control of vphone-cli iOS VMs. Enables AI-driven E2E testing by exposing the VM's display, touch input, and navigation as MCP tools.

45 055
JP
johnzfitch/pyghidra-lite
开发工具

Lightweight MCP server for Ghidra-based reverse engineering with iOS, Linux, and game file support

36 055
AM
akzar1el/mcp-geo
开发工具

AI visibility tracker MCP for ChatGPT, Claude, Perplexity, Gemini & Google AIO. Free OSS/self-host; optional EUR 99 AI Visibility Audit.

44 055
JS
jcfischer/supertag-cli
开发工具

CLI for Tana integration - query, create, sync, and manage Tana workspaces with semantic search and MCP Server

49 055
DD
dremio/dremio-mcp
开发工具

This repo provides an **odel **ontext **rotocol (MCP) server for easing LLM integration with Dremio. If you are new to MCP and MCP Servers take our Dremio MCP Server course on Dremio University...

52 055
TM
tocharianou/mcp-server-kibana
开发工具

A Kibana MCP server implementation that allows any MCP-compatible client (such as Claude Desktop) to access your Kibana instance via natural language or programmatic requests.

75 055
LM
lamemind/mcp-server-multiverse
开发工具

A middleware server that enables multiple isolated instances of the same MCP servers to coexist independently with unique namespaces and configurations.

81 055
SS
scoutapp/scout-mcp-local
开发工具

Scout’s local MCP puts metrics, traces and errors right in your AI agent. For teams that do it all.

30 055
UC
u-c4n/autocad-mcp
开发工具

Live through COM on Windows, or headless through ezdxf anywhere — one typed contract, two engines.

59 055
JL
jochenyang/luma-mcp
开发工具

多模型视觉理解 MCP 服务器,为不支持原生视觉能力的 AI 助手提供统一的图片分析能力。

102 055

Agent Skills

6233 个结果
BR
brianharms/reminder-watch
开发工具

Uses Apple Reminders as a bridge between Claude on your phone and Claude Code on your Mac, dispatching agents from new reminders.

6340
HF
harbor-framework/harbor-index
安全测试

A compact high-signal benchmark for evaluating frontier agents

4040
CL
calibre-labs/reforge-ai-evals
开发工具

Market Map agent eval suite for the Reforge AI Evaluation course

6640
JA
jusi-aalto/strategic-revision
开发工具

A Claude Code skill that turns peer review reports into structured revision roadmaps. Extracts every reviewer request as a separate task, maps dependencies as a directed acyclic graph, validates the...

12040
IW
iamzifei/wechat-article-publisher-skill
开发工具

Publish Markdown or HTML articles to WeChat Official Account drafts with one command. Say goodbye to tedious copy-paste-format workflows.

15340
IY
isoform/yansu-skill
开发工具

"Other agents start cold. Yansu.skill starts warm."

17240
PR
penposs/remix-reference-video-prompt
研究分析

把参考视频拆成可控制、可替换的视频结构,再按用户目标生成可直接使用的视频提示词。

11340
NC
nroadley/creating-oneshot-hero-landing-pages
开发工具

An skill to plan, design, and build video-driven parallax hero landing pages using video scrubbing.

12240
AR
aytuncyildizli/reprompter
开发工具

two intents (improve my prompt / build this whole thing), specifiability routing, One-Shot build prompts, team execution seeded from a build brief — digest

11540
CB
claw-bench/claw-bench
开发工具

The Definitive AI Agent Benchmark Standardized, reproducible evaluation across 314 tasks, 33 domains, and 4 difficulty levels.

17940
KR
kk-r/skillify-skill
开发工具

Skillify watches what you did in a conversation — the tools you used, the corrections you made, the workflow you followed — and captures it as a portable agentskills.io SKILL.md file.

7140
PA
papadopouloskyriakos/agentic-chatops
部署与 DevOps

AI agents that triage infrastructure alerts, investigate root causes, and propose fixes — while a solo operator sleeps.

10740