luma-mcp
Level FSource多模型视觉理解 MCP 服务器，为不支持图片理解的 AI 编码模型提供视觉能力：分析截图、报错、UI 与文档，可接入多家主流视觉大模型。Multi-model vision MCP server that adds image understanding to AI coding models without native vision — analyze screenshots, errors, UI and documents via major vision LLM providers.
Installation
View source repo →Related servers
browser-useBrowser agents and stealth cloud browsers for AI: run web tasks, fill forms, extScrapling🕷️ The BEST Web Scraping framework that handles everything from a single requestUI-TARS-desktopThe Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models andAIHawkAI browser agent: browses, clicks, types, and reads real web pages from plain-Encua-agentCua (Computer Use) Agent for AI-driven computer interactioncua-driverRust-backed Cua Driver SDK and bundled executable for client applications