Cursor 설치 가이드
개발자용 MCP 서버와 함께 자주 쓰이는 AI 코드 에디터.
MCP Servers

Generic markdown vault MCP with hybrid search

A robust integration server that connects MCP (Master Control Program) with Odoo 18.0 ERP system, focusing on efficient data synchronization, API management, and secure communications.

- 🧾 — every MCP tools/call request is now recorded in a dedicated, self-hosted table (wp_wsp_mcp_audit_log): tool name, timestamp (UTC), acting user (or unauthenticated), request IP, and the outcome...

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

Outcome-Based Persistent Memory MCP Server

MCPSafari: Native Safari MCP Server for AI Agents

The open-source trust layer for bringing Claude Code (and other autonomous AI agents) to work — with your security team's approval.

Chat with AI, run tasks on autopilot, and manage your projects — all from one tab.

MCP server to enable an LLM to do basic static triage of a PE.

🔥 MCP Mastery: Build AI Apps with Claude, LangChain and Ollama

is a local stdio MCP server that lets an Agent ask configured multimodal providers to inspect an explicitly supplied image, video, audio file, or music file.

ChatCrystal is a local-first AI PKM app for developers who solve real problems with Claude Code, Cursor, Codex CLI, Trae, and GitHub Copilot.
Agent Skills

Open-source plugin marketplace for Claude Code by DAIR.AI Academy.

- 前任的新对象是谁 - 她关注了谁 - 谁给她点赞 - 她以前发过什么 - 她和谁有共同好友 - 她的每个细节到底是什么意思

Fusion-Fable is a Claude Code skill that runs a hard question through a pipeline. The same prompt is dispatched to several models in parallel — each answering independently with web search and bash,...

Read the launch post for our optimized SpreadsheetBench skill.

A text search engine that supports mixed Chinese and English fuzzy search

A stateless CLI for web search, code search, library docs, and scraping — one binary, no daemon, no API server to run.

本科毕业论文skill:会把你的项目的源码、数据库、截图和文献,按学校模板与样文风格,工程化地写成整合成可追溯、可续写、可审查的本科毕业论文

Desktop AI assistant powered by Claude API

A CLI tool for building Go applications.

Empirically detect the repetitive defaults a model falls back on, then turn those findings into a reusable instruction file that makes future outputs less generic.

From real materials to reports with a fully autonomous & skill-driven researcher.

Productized companion to our paper (arXiv:2606.32014). See Paper & citation.