"author:Gregory78529" matching MCP servers:

Enables AI agents to inspect and live-edit Three.js scenes, materials, shaders, lights and animation in the browser through 69 tools, then turn any previewed change into ready-to-paste Three.js or React Three Fiber code. Also supports website performance audits, video frame capture, and Playwright/Puppeteer test integration.

Enables an MCP client to drive a real browser by stating one outcome at a time, with the Jev model deciding the element, action, and value for each round and pausing before irreversible actions. Also exposes tools to open and act on pages, snapshot or read page content, check yes/no questions, take screenshots, and list or call a page's own WebMCP tools.