adversarial evaluation mcp servers

1 tagged adversarial evaluation, measured the same way as everything else here.

playwright

01

alexsds/ade-workflow

MCP server Claude CodeCodexCursor

Lets the agent drive a real browser: open pages, click, type, take screenshots and read the accessibility tree, using Playwright. Runs locally from the @playwright/mcp npm package.

1 5mo ago A tokens not measured copy · 100% MIT