Claude Desktop 安装指南
支持本地 MCP 配置的桌面客户端。
MCP Servers
blender-ai-mcp lets Claude, ChatGPT, Codex, and other MCP clients control Blender through a stable tool API instead of ad-hoc Python generation.
swagger-mcp is a tool that reads a Swagger 2.0 or OpenAPI 3.0 specification and dynamically generates MCP tools at runtime — one tool per API endpoint.
MCP server for integrating LightRAG with AI tools. Provides a unified interface for interacting with LightRAG API through the MCP protocol.
mcp-repl is an MCP server that gives an agent a persistent Python or R session, kept alive across tool calls.
Production-grade vector memory MCP server for Claude Code. Semantic search, per-project isolation, rules enforcement, team sharing via git.
MCP server and CLI tool that gives AI agents access to YouTube
A Telnet-based MCP tool for Cisco network device CLI, optimized for Cisco IOS devices.
An MCP server that integrates with the Freqtrade cryptocurrency trading bot via its REST API, enabling seamless AI agent interaction for automated trading operation.
A MCP server that provides text-to-image generation capabilities using Stable Diffusion WebUI API (ForgeUI/AUTOMATIC-1111).
Using ffmpeg command line to achieve an mcp server, can be very convenient, through the dialogue to achieve the local video search, tailoring, stitching, playback and other functions
Production-ready starter for with Playwright, TypeScript, Page Object Model, and AI-powered Claude Code agents via MCP.
一个功能强大的知乎收藏夹导出工具，支持将知乎收藏夹（公开和私密）批量导出为 Markdown 格式文件。支持自定义输出路径、跨平台兼容、图片下载和 Obsidian 兼容格式。支持使用大模型API一键生成文章总结。
Agent Skills
High-performance browser automation bridge and multi-instance orchestrator with advanced stealth injection and real-time dashboard.
EmDash is a full-stack TypeScript CMS based on Astro; the spiritual successor to WordPress
Visualize, query, and stream to train on multimodal robotics data.
npx ccusage
Enjoy the magic of Diffusion models!
Found a bug or need help? · Open an issue · Discussions
The official, opinionated, batteries-included toolset for efficient Redux development
Skill of using anytype via agent-runtime with installation instructions for various agents
Memory library for building stateful agents
⭐️⭐️⭐️微服务商城系统 springcloud微服务商城 小程序商城
LiteRT-LM is Google's production-ready, high-performance, open-source inference framework for deploying Large Language Models on edge devices.
Browser4 — an AI-native browser engine for autonomous agents, intelligent extraction, and large-scale web automation.