Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
Bringing official Census Bureau statistics to AI assistants everywhere.
MCP Client 是一个基于 Model Context Protocol 的 Python 客户端实现（使用 Function Calling 和 prompt 两种方式），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。
A Kubernetes Model Context Protocol (MCP) server that provides tools for interacting with Kubernetes clusters through a standardized interface.
A Model Context Protocol (MCP) server that interfaces between Cline and Autodesk Fusion 360. This server exposes Fusion 360 toolbar-level commands as callable tools that map directly to Fusion's API.
MCP (Model Context Protocol) server that gives Claude Code native tools for QuickBooks Online automation.
Imagine having an AI coding assistant that can analyze your codebase, fix bugs, write new features, manage databases, interact with APIs, and automate your entire development workflow - all within...
Model Context Protocol服务器，用于抓取微博用户信息、动态和搜索功能
A Model Context Protocol (MCP) server for WordPress integration, compatible with Windows, macOS, and Linux.
inspiration from https://github.com/mark3labs/mcphost
connects AI agents to ITASCA's numerical modeling software — PFC, FLAC, 3DEC, MPoint, and MassFlow — through the Model Context Protocol.
A persistent, multi-agent server. Continuum gives AI coding agents — Claude Code, OpenCode, Codex, Gemini CLI — a shared, live view of a codebase and a memory that survives across agents and sessions.
A Model Context Protocol (MCP) server that provides tools for reading and extracting text from PDF files, supporting both local files and URLs.
Agent Skills
Agentic prompt workflows as skills. Works with any agentskills.io compatible AI tool.
👆 showing how CLAUDE.md guides AI pair programming in Claude Code.
Curated resources for building and using Agent Skills.
AI Skills for Economists
g3 is a coding AI agent designed to help you complete tasks by writing code and executing commands. Built in Rust, it provides a flexible architecture for interacting with various Large Language...
Pasting raw Gemini or ChatGPT output with zero editing, or running a project with no anti-slop rules at all, is the 2026 equivalent of handing out a business card with an @aol.com email on it.
Repo-Docs: Keep up with the code your agents write. An evidence atlas for agent-built code. Vibe coding makes code move faster than memory.
v2.5.1 — trust-gated review workflows, markdown-first security handoff, expanded framework/database guidance, and a new Python backend skill pack for SDLC delivery.
The official Agent Skills for ClickHouse. These skills help LLMs and agents to adopt best practices when working with ClickHouse and chdb (in-process ClickHouse for Python).
- Click "Use this template" above to create your own AI agent harness. After cloning, run bash scripts/setup-template.sh to customize for your project. See TEMPLATE_SETUP.md for details.
Expose your local web server to the internet with a public URL.
Programmatic memory for long-horizon LLM agents: the harness appends everything to one log, and the agent searches it with code. 97.4% on ARC-AGI-3 (arXiv:2607.20064)