Claude Desktop Руководство установки
Десктопный клиент с поддержкой локальной конфигурации MCP.
MCP Servers
Mapbox Model Context Protocol (MCP) server
A Model Context Protocol (MCP) server for interacting with Twitter.
A that enables AI assistants like Claude, Cursor, and Windsurf to build, test, and debug Tauri® v2 applications.
An extended version by ersatzben and BenCello can be found at: https://github.com/ersatzben/maxmsp-mcp
Vulnerable MCP Servers Lab ==========================
Gearsystem is a very accurate, cross-platform Sega Master System / Game Gear / SG-1000 emulator written in C++ that runs on Windows, macOS, Linux, BSD and RetroArch, with an embedded MCP server for...
Lightweight C++ MCP (Model Context Protocol) SDK
ClaudeR - The Modern Researcher's Toolkit Connect RStudio to Claude Code, Codex, Gemini CLI, or any MCP-based LLM agent for interactive coding, multi-agent orchestration, and automated manuscript...
MCP Server & Config Manager for 14 AI Clients
Designing Enterprise MCP Systems Build, orchestrate, and scale intelligent workflows with the Model Context Protocol Open-source project by Decoding AI
is a Protocol Buffers compiler plugin that generates Model Context Protocol (MCP) servers for your gRPC or ConnectRPC APIs.
English | 中文 | 日本語 | 한국어 | Français | Deutsch
Agent Skills
按语言分区的 （Agent Skills）。面向 Codex、Cursor、Claude Code、Kiro、OpenCode、Trae 等工具，提供可独立安装、可组合调用的测试工作流与测试类型技能。
The verification layer for coding agents
Interactive UI for local node modules inspection
A lightweight desktop app to manage, sync, and organize AI agent skills across 50+ coding tools — Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.
General-purpose Playwright automation for coding agents
Smart tmux session manager
Homepage • Examples • Documentation • CLI References
A collection of agent skills that help with various parts of building a great interface. From animation and UI polish to accessibility and product writing.
Send emails from your terminal 📬
A Claude Code skill bundle for bug hunting and external red-team work - 82 skills, 15 slash commands, 681 disclosed-report patterns curated across 24 core vulnerability classes, plus enterprise...
Skills live under skills/, grouped into buckets:
A model-mediated harness for reliable agentic software development.