screenwright

LegionForge/screenwright
★ 0 stars Python AI/LLM Updated today
AI-powered UI documentation pipeline — Playwright + CV model + MCP server
View on GitHub → 🔍 Audit Wallet Slippage →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "screenwright": {
      "command": "uvx",
      "args": [
        "screenwright"
      ]
    }
  }
}

Or install with pip: pip install screenwright

README Excerpt

<p align="center"> <a href="https://legionforge.org"> <img src="https://assets.legionforge.org/current/logos/legionforge-logo-color.svg" alt="LegionForge" height="64"> </a> </p> A focused documentation screenshot pipeline with an MCP server interface, built by [LegionForge](https://legionforge.org). Screenwright sits on top of Playwright (Python) and a vision model to capture UI screenshots at critical flow points and produce GitHub-documentation-ready output: organized PNGs, structured metadata

Tools (20)

base_urlcapturecheckcheckoutclickdashboardfillharhomepagehoverinvoicemobilemodelnavigateoutput_dirpresspromptproviderselectstorage_state

Topics

automationclaudedocumentationdocumentation-toolmcpmodel-context-protocolopenai-codexplaywrightpythonscreen-recordingscreenshotvision-model