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

MCPyATS brings together the Model Context Protocol (MCP) and Cisco pyATS to build intelligent, distributed agents capable of automating network tasks via natural language.

A lightweight, configurable reverse proxy for routing and load balancing MCP (Model Context Protocol) requests to appropriate backend services based on request content.

Connect ClickHouse to your AI assistants.

Vibetest MCP - automated QA testing using Browser-Use agents

📦️ A fast, secure MCP server that extends its capabilities through WebAssembly plugins.

CodeGraph transforms your entire codebase into a semantically searchable knowledge graph that AI agents can actually reason about—not just grep through.

Browse the web, directly from Cursor etc.

AgentKit: Build multi-agent networks in TypeScript with deterministic routing and rich tooling via MCP.

JSReverser-MCP 是一个面向 JavaScript 逆向分析的 MCP 工具,专门用于帮助开发者在真实浏览器环境中高效定位前端核心逻辑。它 将脚本检索、断点调试、函数 Hook、网络请求追踪、调用链分析、混淆还原和风险评估整合为统一能力,可直接接入 Claude、 Codex、Cursor 等支持 MCP 的客户端。

MCP server that gives AI assistants the power to control a web browser.

Not a path. Not a URL. A handoff that answers back.

Query MCP enables end-to-end management of Supabase via chat interface: read & write query executions, management API support, automatic migration versioning, access to logs and much more.
Agent Skills

The financial data layer for AI agents. Open-source alternative to FactSet / Daloopa / S&P Global for AI agents. 165+ US equities with full SEC filing history. 31 Claude-type skills. 20+ MCP tools.

tooling and Cursor Agent skill: the model interprets the question and organizes evidence; a Python engine performs weighting, normalization, and sensitivity analysis, and emits auditable JSON plus...

An unofficial agent skill for drafting, revising, and auditing clear technical and product documentation.

The core philosophy of fp-pack is simple: It's a pipe-first toolkit for everyday code—approachable, zero-deps, and tree-shakeable.

An AI agent skill that extracts subtitles/transcripts from video platforms and generates structured summary notes with keyframe screenshots. Works with **Cursor** and **Claude Code**.

Extract Markdown, JSON (with bounding boxes), and HTML from any born-digital PDF — deterministically, in milliseconds, on CPU.

design-image-studio 是一个面向创意与设计场景的 Agent Skill。它不是简单地把一句话塞给文生图模型,而是先读取并保留完整的 Claude 设计系统提示词,再把需求整理成设计推理和结构化 brief,最后把这些设计判断压缩成更强的生图 Prompt,并直接调用 Volcengine Seedream 生成图片。

(build 20260317.0002) — 面向所有支持 Skill 的 Agent 平台,提供六维深度安全分析和 S+ ~ D 等级评估

Connect Claude to image generation with Claude Agent Skills — from zero-cost, code-only rendering up to a real diffusion model, then composed into a full app: an that turns a plain-English story into...

CDK Contribution Skill is an Agent Skill that combines multiple specialized subagents, AWS tooling, and Agent SOPs to streamline the entire contribution process.

AI-powered bug bounty hunting toolkit that works with or without subscription.

is a modern, modular JavaScript/TypeScript UI library for building fast, interactive, and beautiful web applications.