Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
It's been a constant struggle trying to understand unfamiliar and complex codebases - managing cognitive overload and trying to imagine how everything fits together.
An enterprise-grade MCP server for legal reasoning and analysis based on the "think" tool concept from Anthropic's engineering blog.
The Upstash MCP server lets your agent manage and debug your Upstash resources directly, across , , , and .
Professional trading assistant supporting with , , and .
Browser MCP gives Claude Code (and any MCP client — Cursor, VS Code agent mode) control of your actual Chrome: your cookies, your sessions, your 2FA.
This is a MCP server for manipulating harmonyOS Device.
This server interacts with the Unstructured API to manage sources, destinations, and workflows. It is not actively maintained and is kept here for reference.
MCP server that connects Claude to Cavalry animation software. Create layers, set attributes, animate with keyframes, render frames, and more — all through natural language.
A MCP server to connect to wolfram alpha API.
mcp-name: io.github.n24q02m/better-notion-mcp
MCP server that triangulates customer support tickets and feature requests to help PMs decide what to build next
business-central-mcp Give AI assistants direct access to Microsoft Dynamics 365 Business Central. Native WebSocket protocol -- no OData, no APIs, no browser automation.
Agent Skills
An EasyEDA Pro API skill package for AI coding tools such as Claude Code, OpenCode, QwenCode, and any other tool that supports the Agent Skills standard.
The map is not the territory. Your prompt is a map; the codebase and the real world are the territory.
ProductSpec is the open standard for product intent. It acts as a Product Harness for AI-native software work: what to build, what not to build, how to prove completion, and when intent changes.
Local-first harness for agent-built codebases. Humans steer, agents execute, maestro is the substrate.
The open-source desktop AI agent that gets work done — an agent that plans and self-corrects, agentic visual workflows, generative UI, and 100+ offline tools in a single self-hostable stack.
一句话：输入一个基金代码，Agent 把基金经理 8 年的每一笔买卖翻出来，拿 12 个月后的真实走势逐笔验对错，最后吐出一份 700KB 的单文件交互报告——K 线战役回放、买卖点验尸、独立性审判、造神检测，全都有。
Together they produce a structured Markdown test plan and a findings report with 10-state verdicts and an explicit SUT / harness / checker / environment blame classification.
LeetCode Helper is a Codex skill for solving LeetCode-style coding interview problems with optimized solutions and detailed explanations.
Deploy any Agent as an API via POST /run . The open, multi-model runtime for AI agents — works with any LLM, on any infrastructure.
A multi-agent marathon simulation built with Google ADK and Gemini. AI agents plan a marathon route through Las Vegas, simulate the environment around it (weather, traffic, crowds), and run the race...
Community-driven agent skills for AI coding assistants
The #1 Terraform skill for Claude Code and Codex, measured by GitHub stars.