Cursor インストールガイド

開発者向け MCP サーバーとよく使われる AI コードエディタ。

11766件

MCP Servers

5533 件
JS
jnhflow21/social-media-toolkit
Developer tools

Public Python SDK, CLI, and MCP server for extracting metadata, text, timed transcripts, media, and supported comments from Douyin, RedNote, Bilibili, and YouTube.

30 099
GB
gokulapap/bugbounty-mcp-server
API development

A production-oriented Model Context Protocol server for authorized bug bounty reconnaissance, bounded security checks, and finding management.

41 099
RM
ravenwits/mcp-server-arangodb
Developer tools

A Model Context Protocol server for ArangoDB

47 099
TS
turbot/steampipe-mcp
Developer tools

Unlock the power of AI-driven infrastructure analysis with Steampipe! This Model Context Protocol server seamlessly connects AI assistants like Claude to your cloud infrastructure data, enabling...

45 099
MC
molml/chemlint
Developer tools

A molecular machine learning MCP server that enables LLMs to handle molecular data

32 099
NU
nirholas/universal-crypto-mcp
Developer tools

██╗ ██╗███╗ ██╗██╗██╗ ██╗███████╗██████╗ ███████╗ █████╗ ██╗ ██║ ██║████╗ ██║██║██║ ██║██╔════╝██╔══██╗██╔════╝██╔══██╗██║ ██║ ██║██╔██╗ ██║██║██║ ██║█████╗ ██████╔╝███████╗███████║██║ ██║...

41 099
FM
f1tz/mcp-for-security-python
Security testing

This is a Python refactored version of the security tools MCP (Model Context Protocol) server collection, implemented using the FastMCP library.

41 099
AF
ai-fe/dify-mcp-server
Developer tools

一个集成 Dify AI API 的 Model Context Protocol 服务器

41 099
AM
awslabs/mcp
Developer tools

Open source MCP Servers for AWS

9360 099
EE
excalidraw/excalidraw-mcp
Developer tools

Fast and streamable Excalidraw MCP App

4839 099
AA
auth0/auth0-mcp-server
Developer tools

MCP (Model Context Protocol) is an open protocol introduced by Anthropic that standardizes how large language models communicate with external tools, resources or remote services.

112 099
JB
jasonjgardner/blockbench-mcp-plugin
Developer tools

https://github.com/user-attachments/assets/ab1b7e63-b6f0-4d5b-85ab-79d328de31db

294 099

Agent Skills

6233 件
BS
base/skills
Developer tools

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
Developer tools

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

6070
SA
slowlyc/agent-gpu-skills
Developer tools

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

15070
AR
ai4s-research/ai4s-skills
Developer tools

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
Developer tools

Every agent skill on GitHub — in one install.

9170
QD
qinghonglin/data2story-skill
Developer tools

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
Developer tools

A Claude Agent Skill for structured persuasion—

18270
FS
frappe/skills
Developer tools

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
Developer tools

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
Developer tools

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
Developer tools

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
Developer tools

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

3470