Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
A type-safe implementation of the official Model Context Protocol (MCP) schema in Rust.
Building Agents with LLM structured generation (BAML), MCP Tools, and 12-Factor Agents principles
Clojure/ClojureScript library for making MCP server and client
A Mattermost integration that connects to Model Context Protocol (MCP) servers, leveraging a LangGraph-based AI agent to provide an intelligent interface for interacting with users and executing...
An MCP server that exposes AWS EC2 pricing data with an option to search by CPU, RAM, networking
ops-mcp-server is an IT operations management solution for the AI era. It achieves intelligent IT operations through the seamless integration of the Model Context Protocol (MCP) and Large Language...
OWASP MCP Taxonomy
A collection of MCP servers for mainland China services. 支持 MCP 的国内服务一览。
This project shows how to implement an MCP (Model Context Protocol) server of Apache ECharts.
A Model Context Protocol (MCP) server that enables AI assistants to interact with Tenzir—a data pipeline engine for security operations.
A lightweight wrapper around mcp-swift-sdk that integrates with LLM Swift libraries such as SwiftOpenAI and SwiftAnthropic to easily create your own MCP Clients in macOS applications.
This is an implementation of the Model Context Protocol (MCP) that integrates with Google's Gemini API to provide analytical thinking capabilities without code generation.
Agent Skills
把梵公子几百小时的视频、直播、网盘素材蒸馏成一个可被 AI 调用的思维框架。不是教你「梵公子会怎么回答」，而是教你「梵公子是怎么思考的」。
Claude Code skill for using Codex CLI as an execution specialist for implementation-heavy coding work, multi-file refactors, and wrapper-based execution flows.
Univer Skill enables AI tools to work directly with spreadsheets, Excel workbooks, and CSV files. Powered by Univer CLI, it brings Git-style diffs, reviews, approvals, and rollbacks to spreadsheet...
A curated collection of operational system prompts and behavioral patterns for AI assistants, LLM agents, and prompt engineers. Each `.skill.
A portable set of for testing and hardening an application . They apply attacker thinking (red team) to find vulnerabilities, then guide you to fix them (blue team).
Human-first multi-agent writing workflow for research, drafting, editing, and fact-checking.
Workspine: plan, execute, and verify AI-assisted work from files in your repo, across sessions and agents.
Stop chasing better models. Engineer the loop.
Claude Code version of skill-autoimprove — auto-improve any CLAUDE.md using Karpathy autoresearch loop
Claude Code skill to extract React components from any production website
Claude Code skill for multi-reviewer peer review of academic papers. Adapted from poldrack/ai-peer-review — uses parallel Claude subagents instead of multiple proprietary LLMs.
build a presentation, convert a PPT/PPTX to web, or create slides for a talk/pitch with unique stylish design. customizable length, styles, format