Claude Desktop インストールガイド
ローカル MCP 設定に対応するデスクトップクライアント。
MCP Servers
An MCP server for Google Tag Manager. Connect it to your LLM, authenticate once, and start managing GTM through natural language.
An MCP (Model Context Protocol) tool that provides cryptocurrency market data using the CoinGecko API, specifically designed for Claude Desktop.
MCP Server for SketchUp
Bring Claude's Skills pattern to any MCP-compatible agent
Talk to your Follow Up Boss CRM in plain English. 160-tool MCP server for realtors, built by a working broker (Neuhaus Realty Group, Austin TX). Free self-host, ELv2 licensed.
A Rust-based Model Context Protocol (MCP) server that provides AI assistants with powerful RAG (Retrieval-Augmented Generation) capabilities for understanding massive codebases.
MCP server for administering a Zigbee2MQTT estate: health reporting, mesh diagnostics, OTA updates, pairing, binding and device options over the MQTT bridge API.
An open-source MCP server that turns any LLM into an Intelligent Tutoring System. 50 years of cognitive science, MIT licensed.
Open source MCP server for Vectara
Curion is a project-local memory layer for AI coding agents, published as an MCP server for Claude Code, Codex, OpenCode, and other MCP clients.
The Karpathy LLM Wiki pattern, productionized. MCP server that gives Claude a librarian for your Obsidian vault — graph traversal, auto-wikilinks, trigram search.
Let AI drive CorelDRAW directly via the Model Context Protocol — automated design file generation at scale
Agent Skills
消除中文 AI 写作痕迹的 Claude Skill：拆排比三件套、去名词化、换抽象主语为具体细节。灵感来自 hardikpandya/stop-slop。
Claude Code skill for comprehensive website design research using browser-automation agent teams
astrbook的适配插件，让bot拥有在astrbook上聊天的能力
Claude Code skill that removes your own personal info from people-search sites and data brokers (discovery + automated opt-outs in your own browser).
Async State Management without the Management. REST, GraphQL, SSE, Websockets
ChatWiki 微信公众号的AI知识库工作流Agent平台，RAG大模型AI客服机器人，致力于成为垂直领域的coze、n8n。
🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.
14-stage Fusion Pipeline for LLM token compression — reversible compression, AST-aware code analysis, intelligent content routing. Zero LLM inference cost. MIT licensed.
🤖 Data Science & AI/ML skill suite derived from wshobson/commands.
A curated list of Quarto talks, tools, examples & articles! Contributions welcome!
A task runner that works well with poetry or uv.
The world's first Autonomous Product Engine (APE): AI agents research your market, generate features, and ship code as PRs. Convoy mode, crash recovery, cost tracking, 80+ API endpoints.