{
  "slug": "playwright-mcp",
  "name": "playwright-mcp",
  "url": "https://github.com/microsoft/playwright-mcp",
  "cat": "agtools",
  "group": "claude",
  "tagline": "Browser automation MCP (Microsoft)",
  "price": "Free",
  "tier": "free",
  "pick": true,
  "what": "Drives a real browser and exposes the page to the model as a <b>structured accessibility snapshot</b> rather than a screenshot — so the agent targets elements deterministically without vision or pixel guessing. Adds network mocking, storage state, tracing, video and PDF generation. ~36k stars.",
  "why": "<b>This is how Claude checks its own work.</b> Have it load the article page, verify the layout at three breakpoints, confirm images lazy-load, and catch the broken nav before you do. The accessibility-tree approach doubles as a free a11y audit on a publication site.",
  "install": "claude mcp add playwright npx @playwright/mcp@latest",
  "category": {
    "key": "agtools",
    "name": "Agent tools & orchestration",
    "desc": "Browsers, crawlers, routing, multi-agent workspaces.",
    "group": "claude",
    "groupName": "Claude Code toolkit"
  },
  "freshness": null,
  "health": {
    "ok": true,
    "status_code": 200,
    "final_url": null,
    "checked_at": "2026-08-18T20:13:57.562+00:00"
  },
  "corrected_at": null,
  "upstream_changed_at": null
}