Claude Desktop Руководство установки
Десктопный клиент с поддержкой локальной конфигурации MCP.
MCP Servers

Model Context Protocol, or MCP, is an open protocol that standardizes how applications provide context to LLMs.

OmniMCP provides rich UI context and interaction capabilities to AI models through Model Context Protocol (MCP) and microsoft/OmniParser.

A distributed runtime system for federated AI services with edge computing capabilities.

Implementation of a model context protocol (MCP) client that connects to an MCP server using HTTP streamable (recommended) transport and displays the conversation in a chat-like UI.

A comprehensive collection of courses and tutorials for learning the - an open protocol that standardizes how AI applications connect to external tools and data sources.

This implementation is based on the Model Context Protocol (MCP) put forward by Anthropic. For more information on MCP, please have a look at their official documentation.

Index your documentation from across the sources and serve it via the Model Context Protocol (MCP) and REST API.

The is a professional-grade Python implementation of the . It provides a structured environment for Large Language Models (LLMs) to interact with external tools and knowledge bases through a...

⚠️ : This registry is currently in active development and testing phase. The API and data structure may change. Not recommended for production use yet.

guMCP is an open-source collection of Model Context Protocol (MCP) servers that can be run both remotely and locally.

MCP server that gets Claude to 97.9% (188/192) on a real coding benchmark at -80% active tokens and -83% wall time, vs 78.3% plain. Structural code navigation + persistent memory engine.

Official CLI for muapi.ai — generate images, videos & audio from the terminal. MCP server, 14 AI models, npm + pip installable.
Agent Skills

“他们都叫我小唐人!他们都叫我臭唐氏!说谁是唐氏呢!!!骂谁唐氏!” “关注永雏塔菲喵,关注永雏塔菲谢谢喵!”

A prose-native implementation of Vincent Driessen's git-flow branching model.

一个真正适合职场人的 PPT Skill。把文档丢给你的 AI Agent,每一页都自带编辑控制台的 PPT Skill——不满意的地方直接在浏览器里改,改完还能一键导出成真实的、可编辑的 PPTX。

Human-first multi-agent writing workflow for research, drafting, editing, and fact-checking.

Workspine: plan, execute, and verify AI-assisted work from files in your repo, across sessions and agents.

— 此 skill 定義了「完成任務後必須詢問下一步」的強制模式,不可跳過、不可例外。

Track your AI coding tool token usage and sync to vibecafe.ai.

Codex / Claude Code 在使用 Plan 模式处理产品设计、研究规划等复杂任务时,会自作主张地进行一些决定,最终导致「反复的方案调整」。

Claude Code version of skill-autoimprove — auto-improve any CLAUDE.md using Karpathy autoresearch loop

A comprehensive UX and design strategy system for AI tools. 17 specialized skills and 6 agents that cover the full product design practice — from early strategy and research through experience...

Claude Code skill to extract React components from any production website

Claude Code skill for multi-reviewer peer review of academic papers. Adapted from poldrack/ai-peer-review — uses parallel Claude subagents instead of multiple proprietary LLMs.