Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
MCP server for Polyrouter API - unified prediction market aggregator
ExternalAttacker is a powerful integration that brings automated scanning capabilities with natural language interface for comprehensive external attack surface management and reconnaissance.
A Model Context Protocol (MCP) server for stock data retrieval
A Go implementation of the Model Context Protocol (MCP) with comprehensive streaming HTTP support. This library enables efficient communication between client applications and tools/resources.
The Model Context Protocol (MCP) is an open-source implementation that bridges Jenkins with AI language models following Anthropic's MCP specification.
This project implements a WebSocket-based bidirectional audio streaming application integrated with Amazon Nova Sonic model for real-time speech-to-speech conversations.
A production-ready MCP (Model Context Protocol) server that enables to control Blender directly through natural language.
A Model Context Protocol (MCP) server implementation for the Gmail API, providing a standardized interface for email management, sending, and retrieval.
✨用Java实现的MCP，爬取最新热点新闻，允许LLM调用。告别信息茧房，用AI洞悉世界。
Browser and desktop automation with an MCP server for AI assistants. Record macros or write JavaScript to automate websites, extract data, and control desktop apps with OCR and image recognition.
MCP Client 是一个基于 Model Context Protocol 的 Node.js 客户端实现（使用 Function Calling），它允许您的应用连接到各种 MCP 服务器，并通过大语言模型（LLM）与这些服务器交互。MCP（模型上下文协议）是一个开放协议，用于标准化应用程序向 LLM 提供上下文的方式。
Ollama MCP Agent allows you to use LLM models locally on your PC for free. Using Ollama's locally installed LLM models along with MCP (Model Context Protocol) additional features, you can easily...
Agent Skills
Official skills for the GLM family of models, designed for agent architectures including Claude Code, OpenCode, OpenClaw, AutoClaw, and other AI coding agents.
A Claude Code skill that turns any folder of static HTML pages into a . Highlight text, click an element, leave a note — the comment lands in a local inbox that Claude reads and responds to by...
1. 先检查 Word 自动化环境 2. 先审计，再决定怎么改 3. 学校明确规定的格式严格执行 4. 学校没规定的格式默认保留现状 5. 最后导出 PDF 逐页复核
The thinnest possible bridge from the LLM to Chrome. — just every CDP method as a typed JS call.
Skills for . Your agent (the orchestrator) writes a self-contained brief, hands it to an implementer CLI, then reviews the diff and commits — staying the reviewer the whole way.
Essays and writing behind this toolkit live at vexjoy.com.
A Claude Code skill that turns any API into a working CLI, then wraps that CLI in a skill. Point it at API docs, a live URL, or a peek-api capture and get a dual-mode Commander.
A Claude skill that automatically posts personalized, authentic comments in your target communities.
16 cohesive skills + 2 custom subagents walk an idea from brainstorm through implementation, with checkpoints throughout where you stay in control.
Reusable XCrawl skill definitions for multi-agent runtimes, focused on API-first web data workflows. Canonical repository: https://github.com/xcrawl-api/xcrawl-skills
A simple skill that will make your Agent create beautiful Infographics
Claude Code skills that let Claude interact with Google Scholar through Chrome DevTools MCP.