Cursor 安装指南

常与开发类 MCP Server 搭配使用的 AI 代码编辑器。

9640个结果

MCP Servers

5055 个结果
TA
threemoonslab/agents-shipgate
开发工具

Local-first and static by default — no agent execution, tool calls, LLM calls, or network access.

88 070
NM
nesquikm/mcp-rubber-duck
开发工具

An MCP (Model Context Protocol) server that acts as a bridge to query multiple LLMs -- both OpenAI-compatible HTTP APIs and CLI coding agents.

174 070
AL
akshayvkt/lenny-mcp
开发工具

Search 284 episodes of Lenny's Podcast transcripts directly from Claude. Get instant access to product wisdom from guests like Shreyas Doshi, Julie Zhuo, Brian Chesky, and hundreds more.

35 070
PP
pfldy2850/py-mcp-naver
开发工具

A server implementation for Naver OpenAPI using the Model Context Protocol (MCP). This project provides tools to interact with various Naver services, such as searching blogs, news, books, and more.

114 070
MA
mikeyny/ai-image-gen-mcp
开发工具

An MCP (Model Context Protocol) server implementation for generating images using Replicate's black-forest-labs/flux-schnell model.

123 070
AW
agricidaniel/wp-mcp-ultimate
开发工具

Connect WordPress to AI in one click. A self-contained MCP (Model Context Protocol) server plugin with 58 WordPress abilities -- manage posts, pages, media, users, plugins, menus, comments, and more...

139 070
DG
developzir/gepa-mcp
开发工具

I'm not quite sure this works as is 😂 You may need to ask the model you're working with to clean it up:

51 070
EB
eunomia-bpf/mcptrace
开发工具

A minimal MCP (Model Context Protocol) server that provides AI assistants with access to bpftrace kernel tracing capabilities.

72 070
YW
yranjan06/webghosting-mcp
浏览器自动化

Intelligent stealth browser MCP server for AI agents with 30 tools, 22 anti fingerprint scripts, and LLM powered extraction.

31 070
ES
esinecan/skynet-agent
分析与监控

What if AI could not only access memories, but consciously choose what to remember? With MCP tool access fully supported?

135 070
AK
aywengo/kafka-schema-reg-mcp
部署与 DevOps

A comprehensive Message Control Protocol (MCP) server for Kafka Schema Registry.

32 070
DO
danielmeppiel/oracle-mcp-server
开发工具

A powerful Model Context Protocol (MCP) server that provides contextual database schema information for large Oracle databases, enabling AI assistants to understand and work with databases containing...

127 070

Agent Skills

4585 个结果
OO
opencoworkai/open-codesign
开发工具

Open-source Claude Design alternative. One-click import your Claude Code / Codex API key. Prompt → prototype / slides / PDF. Multi-model (Claude, GPT, Gemini, Kimi, GLM, Ollama).

726555
AO
archieindian/openclaw-superpowers
开发工具

44 plug-and-play skills for OpenClaw — self-modifying AI agent with cron scheduling, security guardrails, persistent memory, knowledge graphs, and MCP health monitoring.

7255
AI
ayghri/i-have-adhd
API 开发

A skill to stop your coding agent from burying the answer. ADHD-friendly output.

308255
TA
tma1-ai/tma1
开发工具

A monolith for your agent's loop. Silent until it talks back.

11655
SA
somnus0x/agt-skill-pack
开发工具

ฝรั่งแจกพร้อมท์ฟรีกัน ทำไมคนไทยต้องซื้อพร้อมท์

7455
CW
claude-world/director-mode-lite
开发工具

Direct work across Claude Code, Codex CLI, and Grok Build.

8155
SS
sanqiufong/slides-from-anything
开发工具

Slides from Anything is a local-first presentation agent workflow for turning source material into delivery-ready decks.

12955
RB
realtimelogic/bas
开发工具

This repository contains the amalgamated C source code for Real Time Logic's embedded web and application server libraries:

9355
JC
jeffallan/claude-skills
代码审查

67 Specialized Skills for Full-Stack Developers. Transform Claude Code into your expert pair programmer.

1万55
DG
duolahypercho/gauntlet-loop
数据科学与机器学习

Matt Shumer's aim prompt as a slash command — build a game against a named reference. Fill the three paragraphs. Run them. Stop when you stop it.

13255
GS
godgod126/self-improving-for-codex
数据科学与机器学习

让 Codex 通过 AGENTS.md 与本地 Markdown 记忆文件形成可审计、可维护的长期改进闭环。

12955
CS
christopherarter/superpowers-reasonix
开发工具

Process skills that give a Reasonix coding agent the disciplines of a careful engineer: write the test first, debug from evidence, plan before coding, verify before claiming done.

9455