# executeautomation/mcp-playwright

Playwright Model Context Protocol Server - Tool to automate Browsers and APIs in Claude Desktop, Cline, Cursor IDE and More 🔌

Repository: https://github.com/executeautomation/mcp-playwright
Canonical: https://ross.abutalabs.com/products/mcp-playwright
Homepage: https://executeautomation.github.io/mcp-playwright/
Language: TypeScript
License: MIT
License Family: permissive
Last push: 2025-12-13T04:28:38+00:00

## Health v2 (maintenance only)
Score: 47/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 57, release rhythm 35, longevity 45
- inputs: {"age_days": 638, "days_push": 263, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5635, forks 533 (observed 2026-08-28T04:09:26.596380+00:00)

## What it is
A Model Context Protocol (MCP) server that exposes Playwright browser automation to LLM clients like Claude Desktop, Cline, and Cursor IDE. It lets AI assistants navigate web pages, take screenshots, scrape content, execute JavaScript, emulate devices, and test APIs using natural language.

## Use cases
- automate browser testing with AI assistants
- let Claude take screenshots of web pages
- scrape web page content via an LLM
- test web UIs and APIs in plain English
- emulate mobile devices like iPhone 13 during testing
- generate Playwright test code from natural language

## When to choose
- you use Claude Desktop, Cursor, Cline, or another MCP client and want browser automation
- you want AI-driven UI and API testing without writing code
- you need web scraping or screenshots driven by an LLM

## When to avoid
- you need a standalone CI test suite without an LLM client
- you want the official Microsoft Playwright MCP implementation instead
- your automation does not involve browsers or HTTP APIs

## Facets
- artifact type: service
- maturity: active
- function: mcp, testing, web-scraping, e2e-testing, http-client, agent-framework
- domain: developer-tools, testing, large-language-models
- platform: cross-platform, cli
- tags: playwright, browser-automation, mcp-server, claude-desktop, cursor, api-testing, screenshots, automation, ai-agents, nodejs

## Member repositories
- executeautomation/mcp-playwright (main) score 47

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:26.596380+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:55:19.612743+00:00, confidence not recorded.
  - readme: https://github.com/executeautomation/mcp-playwright (fetched 2026-08-28T04:09:26.596380+00:00, sha e0db5f6c96d4)
  - homepage: https://executeautomation.github.io/mcp-playwright/ (fetched 2026-08-29T08:50:09.428717+00:00, sha 2e76452d685f)
- Data as of 2026-08-30T08:39:29.467469+00:00.