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
Figma MCP build with Rust, server with full read/write access via plugin (no REST API, no rate limits, 73 tools)
MCP server for Web3 protocol documentation — EIPs, ERCs, BIPs, SIMDs, Cosmos ADRs, Polkadot RFCs, contract registry
A FastMCP server implementation for controlling Apple Music (formerly iTunes) on macOS through AppleScript commands.
Git-backed wiki engine with MCP server — build knowledge that compounds
An MCP server that validates, auto-fixes, and scaffolds TwinCAT 3 XML files. Connect it to any LLM client to give your AI assistant reliable, deterministic TwinCAT code quality tooling — structural...
MCP tools for Novyx governed actions, shared memory, audit, rollback, and evidence workflows.
MCP 支持两种通信传输方法：STDIO（标准输入/输出）或 SSE（服务器推送事件），两者都使用 JSON-RPC 2.0 进行消息格式化。STDIO 用于本地集成，而 SSE 用于基于网络的通信。
WaveSpeed MCP server — run any model on the live catalog (image, video, audio, 3D) with schema introspection, @path file upload, and price quotes
🎨 AI-powered UI/UX design intelligence - 1519+ curated design resources through MCP | React, Vue, Next.js, Flutter & more
This project is a Python-based CapCut processing tool that offers the following core functionalities:
Welcome to the Kanban MCP project! 🎉 This project integrates Planka kanban boards with Cursor's Machine Control Protocol (MCP) to enable AI assistants like Claude to manage your kanban boards.
📚 MCP server for academic paper search and download.
Agent Skills
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。
- Manage Claude Code, OpenAI Codex, Google Gemini, OpenCode, and custom AI agents from one powerful command-line interface.
(As usual, XKCD has a comic for this. Appropriately enough, the comic is out of date.)
中文内部技术写作的 agent skill。约束设计文档、评审稿、postmortem、分享稿等场景的语气、句法、结构，让产出贴近技术汇报，避开营销稿和散文气质。
LeetCode Helper is a Codex skill for solving LeetCode-style coding interview problems with optimized solutions and detailed explanations.
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...
Reusable skills and steering that teach AI coding agents how to apply the AWS Well-Architected Framework. One set of playbooks, .
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.
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.
agnix Lint agent configurations before they break your workflow
Browser Control lets trusted coding agents run Playwright against your existing Chromium-family browser.
Everything you need to know about OpenCode — from your first prompt to custom agents, skills, plugins, and MCP integrations.