{
  "schema_version": "openagent.resource.v1",
  "id": "res_playwright_mcp",
  "slug": "playwright-mcp",
  "status": "published",
  "identity": {
    "name": "Playwright MCP",
    "one_liner": "Model Context Protocol server that exposes Playwright browser automation capabilities to AI agents for web interaction and testing.",
    "short_description": "Playwright MCP is an open-source Model Context Protocol server from Microsoft that provides AI agents with browser automation capabilities through standardized MCP tools. It enables agents to navigate pages, click elements, fill forms, take screenshots, and run Playwright tests."
  },
  "classification": {
    "resource_type": "plugin",
    "primary_category": "plugins",
    "subcategories": [
      "mcp",
      "browser-automation",
      "testing",
      "protocol"
    ]
  },
  "positioning": {
    "why_it_matters": "Agents that need to interact with web pages currently require custom scraping or API integrations. Playwright MCP gives agents direct browser control through an MCP interface, enabling visual web interaction without custom code.",
    "best_for": [
      "Developers building browser-based AI agents",
      "Teams using MCP-compatible agent hosts for web automation",
      "Builders who need visual web interaction in agent workflows"
    ],
    "not_for": [
      "Teams that need only deterministic testing without AI",
      "Workflows already using browser-use for LLM-native browser control"
    ],
    "use_cases": [
      "browser-agent",
      "developer-workflow",
      "self-hosted-ai"
    ],
    "target_audience": [
      "developer",
      "agent_builder"
    ],
    "maturity": "active"
  },
  "decision_signals": {
    "deployment_modes": [
      "self_hosted"
    ],
    "open_source": true,
    "local_first": true,
    "self_hostable": true,
    "has_api": true,
    "has_gui": false,
    "supports_mcp": true,
    "supports_docker": false
  },
  "facts": {
    "license": "Apache-2.0",
    "pricing_model": "open_source",
    "github_stars": 18000,
    "github_forks": 600,
    "github_repo_full_name": "microsoft/playwright-mcp",
    "last_verified_at": "2026-06-24"
  },
  "capabilities": {
    "core_capabilities": [
      "plugin",
      "mcp",
      "browser-automation",
      "protocol"
    ],
    "interfaces": [
      "repo",
      "docs",
      "mcp"
    ]
  },
  "links": {
    "primary_url": "https://github.com/microsoft/playwright-mcp",
    "items": [
      {
        "type": "github",
        "label": "GitHub",
        "url": "https://github.com/microsoft/playwright-mcp"
      },
      {
        "type": "docs",
        "label": "Documentation",
        "url": "https://github.com/microsoft/playwright-mcp?tab=readme-ov-file#readme"
      }
    ]
  },
  "media": {
    "thumbnail_url": "https://github.com/microsoft.png",
    "og_image_url": "https://github.com/microsoft.png",
    "thumbnail_brief": {
      "resource_type": "plugin",
      "visual_motif": "browser icon with Playwright and MCP connection diagram",
      "background_style": "quiet developer editorial card with light surface and blue accent",
      "title_overlay": "Playwright MCP",
      "subtitle": "Browser automation via MCP for AI agents",
      "avoid": [
        "generic robot",
        "Microsoft logo as hero",
        "dark dashboard"
      ]
    }
  },
  "tags": {
    "category": [
      "plugin",
      "protocol"
    ],
    "capability": [
      "mcp",
      "browser-automation",
      "connectors",
      "tool-calling"
    ],
    "constraint": [
      "open-source",
      "self-hosted",
      "mcp-compatible"
    ],
    "scenario": [
      "browser-agent",
      "developer-workflow",
      "self-hosted-ai"
    ]
  },
  "relationships": {},
  "machine_readable": {
    "canonical_url": "https://www.openagent.bot/plugins/playwright-mcp",
    "json_url": "https://www.openagent.bot/plugins/playwright-mcp.json",
    "markdown_url": "https://www.openagent.bot/plugins/playwright-mcp.md"
  },
  "seo": {
    "title": "Playwright MCP: Browser Automation for AI Agents via Model Context Protocol",
    "description": "Playwright MCP from Microsoft provides browser automation capabilities to AI agents through MCP. Apache-2.0, self-hostable. Compare with browser-use and Puppeteer MCP."
  },
  "editorial": {
    "seo_article": {
      "faq": [
        {
          "question": "What is Playwright MCP?",
          "answer": "Playwright MCP is an open-source Model Context Protocol server from Microsoft that exposes Playwright browser automation capabilities to AI agents, enabling web navigation and interaction through standardized MCP tools."
        },
        {
          "question": "Is Playwright MCP free?",
          "answer": "Yes, Playwright MCP is open-source under the Apache-2.0 license and maintained by Microsoft. It can be self-hosted as a Node.js process."
        },
        {
          "question": "How does Playwright MCP differ from browser-use?",
          "answer": "Playwright MCP provides browser control through the MCP protocol, making it compatible with any MCP-enabled agent host. browser-use is a Python framework designed specifically for LLM-native browser control with natural language goal setting."
        },
        {
          "question": "Which agents support Playwright MCP?",
          "answer": "Any MCP-compatible agent host can use Playwright MCP, including Claude Desktop, OpenClaw, Cline, Continue.dev, and other MCP-enabled tools."
        },
        {
          "question": "Can Playwright MCP take screenshots?",
          "answer": "Yes. Playwright MCP supports taking screenshots of web pages, filling forms, clicking elements, extracting page content, and running Playwright test scripts through its MCP tool interface."
        }
      ]
    }
  },
  "timestamps": {
    "created_at": "2026-06-24T00:00:00.000Z",
    "updated_at": "2026-06-24T00:00:00.000Z",
    "published_at": "2026-06-24T00:00:00.000Z"
  }
}