Claude Desktop 安装指南
支持本地 MCP 配置的桌面客户端。
MCP Servers
A Model Context Protocol (MCP) server that provides web search functionality using Perplexity AI's API.
MCP Server for code graph analysis and visualization by CodeGPT
Control and query Home Assistant from Claude and other LLMs — a Model Context Protocol (MCP) server.
A Model Context Protocol (MCP) server that provides AI assistants with secure access to the Kite Connect trading API.
allows you to control from using the . It consists of:
curl https://cryptocurrency.cv/api/news • LLM Docs • Full API Docs • OpenAPI
Lightweight MCP server for Spotify
: This server only works on Windows operating systems due to its dependency on Windows-specific COM interfaces.
Modern AI-powered coding assistants (like Cursor, Cline, Roo Code, etc.) excel at understanding code structure and syntax but often struggle with the specifics of rapidly evolving libraries and...
Unity MCP Server — 268 tools for AI-assisted game development. Connect Claude, Cursor, or any MCP client to Unity Editor & Unity Hub.
This is a Model Context Protocol (MCP) server for the Facebook Ads Library.
A Model Context Protocol (MCP) server for MetaTrader 5, allowing AI assistants to interact with the MetaTrader 5 platform for trading and market data analysis. Documentation
Agent Skills
The definitive list that answers "I want to do X in Python, which tool should I use?"
YYLO (why-lo): AI coding-agent orchestration CLI with equivalent yylo and yy launchers.
Memory library for building stateful agents
⭐️⭐️⭐️微服务商城系统 springcloud微服务商城 小程序商城
Not quite vibe-coding. Not quite boomer coding. Something else.
Graph-based issue tracker for AI agent coordination
Copy this repo into any project. Claude Code, Codex, and other agentic tools then follow the same gated process — spec, plan, task cards, implementation, verification, review — before code reaches...
:warning: — The Windows App Development CLI (winapp CLI) is experimental and in active development. We'd love your feedback! Share your thoughts by creating an issue.
LiteRT-LM is Google's production-ready, high-performance, open-source inference framework for deploying Large Language Models on edge devices.
Independently written prompt templates for building AI coding agents, inspired by patterns observed in Claude Code codebase.
A curated list of reusable skills, workflows, and tool-backed capabilities for AI agents.
Blocks specific sites from appearing in Google search results