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

Real-time cost tracking for every MCP tool call across Cursor, Claude Desktop, Windsurf, and VS Code.

aula-mcp er en server der sidder mellem en MCP-klient (LLM) og Aula — et interface, ikke meget mere. Du vælger selv klient (Claude Code, Claude Desktop, ChatGPT, Cursor, Ollama, LM Studio osv.

Specification and documentation for the Healthcare Model Context Protocol. This builds on top of the base Model Context Protocol

Your Syscall Factory (feat. Canterlot's Gate)

MCP server for analyzing & generating docs for React code locally

[//]: # ([](https://github.com/sitbon/magg/actions/workflows/test.

Official remote MCP server for Trello.

Connect your AI assistant (Claude or ChatGPT) to DottedSign — create signing tasks, track document status, manage templates, and more using natural language.

SurfSense is the , an open web research platform with live data connectors. Your agents research the live web with structured data from , through one or .

Hands-on lab of ten Model Context Protocol (MCP) challenges reproduced from real CVEs and public incident reports.

ros2-mcp-server is a Python-based server that integrates the Model Context Protocol (MCP) with ROS 2, enabling AI assistants to control robots via ROS 2 topics.

MCP Server for Teenage Engineering EP-133 KO-II
Agent Skills

Official Convex plugins for AI coding agents, providing development tools for building reactive backends with TypeScript.

Curated AI coding agent skills and CLAUDE.md / AGENTS.md playbooks for Codex, Claude Code, Cursor, OpenClaw, Autohand Code, Trae, and other SKILL.md-compatible tools.

是一个**,支持 Claude Code、Codex、Cursor、GitHub Copilot、Gemini CLI 等主流 AI 编程工具。

A curated list of awesome tools, skills, plugins, integrations, extensions, frameworks, and other resources for developers working with .

SkillOps = Validate, manage, and deliver skills at scale.

Lazyweb gives AI coding agents real product screenshots, UI references, and design research workflows before they build or critique an interface.

Standalone engineering skills for Claude Code and Codex: review, audit, optimization, testing, product discovery, architecture, and safe publishing.

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)

Curated list of 150+ tools, skills, subagents & plugins for OpenAI Codex CLI

前端 · 后端 · 移动端 · DevOps · AI 设计工具 — 生产级品质,独立安装。

A curated library of 68 best-practice, plug-and-play product management skills covering the complete product lifecycle - plus templates, workflows, and 200+ real-world sample outputs that set the...

Skills based on the Layered Rails book and beyond