Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers

An AI Gateway, registry, and proxy that sits in front of any MCP, A2A, or REST/gRPC APIs, exposing a unified endpoint with centralized discovery, guardrails and management.

Integrate QuantConnect's research environment, statistical analysis, and portfolio optimization into your AI workflows. Locally hosted, secure & capable of dramatically improving productivity

Official MCP server implementation for accessing Open Targets Data

Production-grade MCP server and AI tools for the Godot engine. A Snap to install. Totally free and fun.

A Model Context Protocol server that provides search capabilities using a CSE (custom search engine).

A comprehensive collection of Model Context Protocol (MCP) servers, empowering AI models with enhanced capabilities through standardized integrations.

Self-hosted CMS that works human or headless: full admin UI plus REST and MCP APIs, built-in semantic search and site chat, and content forking, versioning, diff/merge review, templates, approvals,...

A Model Context Protocol (MCP) server for the Open Library API that enables AI assistants to search for book and author information.

A powerful Python recreation of Claude Code with enhanced real-time visualization, cost management, and Model Context Protocol (MCP) server capabilities.

A comprehensive Model Context Protocol (MCP) server for penetration testing and cybersecurity operations, providing seamless integration between Kali Linux tools and MCP-compatible clients.

MCP (Model Context Protocol) server for Biothings.io

This is a Model Context Protocol (MCP) server implementation built with .NET 9.0. The MCP server provides a communication protocol for facilitating interactions between various components in a...
Agent Skills

A Claude Code plugin that adds DuckDB-powered skills for data exploration and session memory.

Desktop AI assistant powered by Claude API

一個 Claude Code skill,讓 AI 學會你的 Facebook 講話風格、幫你規劃內容、自動發到 FB / IG / Threads / X。

The thinnest possible bridge from the LLM to Chrome. — just every CDP method as a typed JS call.

You are a distinguished fellow on this project who is retiring. Your final task: build a complete skill library under .

AgentOps is the operations layer for agentic engineering.

每天定时 12:00 更新,数据从 2024-01-01 开始拉取,每天累计更新。

Point it at your organization's own tools, or use the pre-built graph, and ctx recommends the smallest useful bundle for the current development window.

A simple skill that will make your Agent create beautiful Infographics

AsyncReview uses Recursive Language Models (RLM) to go beyond simple diff analysis. It autonomously explores your repository, fetches relevant context, and verifies its findings in a secure sandbox...

This repository contains the source code for Modal's official SDKs.

CatchMe: Make Your AI Agents Truly Personal