Playwright Mcp 1.0.0

Browser automation via Playwright MCP server. Navigate websites, click elements, fill forms, extract data, take screenshots, and perform full browser automat...

Security Scan

The skill's requirements, instructions, and files align with a Playwright MCP browser-automation toolset and do not request unrelated credentials or suspicious installs, but it exposes powerful browser-level capabilities that you should use with caution.

Purpose & Capability

Name/description match the declared requirements: the skill needs playwright-mcp/npx and documents installing @playwright/mcp. No unrelated binaries, env vars, or credentials are requested.

Instruction Scope

SKILL.md stays on-topic for browser automation, but includes powerful primitives (browser_evaluate to run arbitrary JS, browser_choose_file to upload files, navigation to arbitrary URLs). Those capabilities are expected for a browser automation skill but can be used to exfiltrate data or access internal endpoints if misused. The doc mentions allowed-hosts / blocked-origins and sandboxing but leaves defaults and enforcement unclear.

Install Mechanism

No embedded install script is executed by the registry; installation is via npm/npx (@playwright/mcp) which is the expected mechanism for Playwright tools. No ad-hoc downloads or obscure URLs are used.

Credentials

The skill requires no environment variables or credentials, which is proportionate to its stated functionality.

Persistence & Privilege

always is false and model invocation is allowed (the platform default). The skill does not request persistent system-wide privileges or modify other skills' configurations.

Assessment

This skill appears to be what it claims: a Playwright MCP front-end. Before installing, consider these practical security steps: (1) Verify the npm package (@playwright/mcp) is the expected upstream and review its release page; (2) Restrict the MCP server with --allowed-hosts and avoid using --no-sandbox or --ignore-https-errors unless necessary; (3) Treat browser_evaluate and file-upload tools as sensitive: do not allow the agent to execute arbitrary JS on pages that handle secrets or to upload local files you don't trust; (4) Run the MCP server in an isolated environment (container/VM) if you will automate untrusted sites or internal networks; (5) Monitor network activity and outputs produced in --output-dir. These mitigations address the legitimate but powerful capabilities of browser automation; the skill itself is coherent with its description.

Playwright MCP Skill

Browser automation powered by Playwright MCP server. Control Chrome, Firefox, or WebKit programmatically.

Installation

npm install -g @playwright/mcp
# Or
npx @playwright/mcp

Install browsers (first time):

npx playwright install chromium

Quick Start

Start MCP Server (STDIO mode)

npx @playwright/mcp

Start with Options

# Headless mode
npx @playwright/mcp --headless

# Specific browser
npx @playwright/mcp --browser firefox

# With viewport
npx @playwright/mcp --viewport-size 1280x720

# Ignore HTTPS errors
npx @playwright/mcp --ignore-https-errors

Common Use Cases

1. Navigate and Extract Data

# MCP tools available:
# - browser_navigate: Open URL
# - browser_click: Click element
# - browser_type: Type text
# - browser_select_option: Select dropdown
# - browser_get_text: Extract text content
# - browser_evaluate: Run JavaScript
# - browser_snapshot: Get page structure
# - browser_close: Close browser

2. Form Interaction

1. browser_navigate to form URL
2. browser_type into input fields
3. browser_click to submit
4. browser_get_text to verify result

3. Data Extraction

1. browser_navigate to page
2. browser_evaluate to run extraction script
3. Parse returned JSON data

MCP Tools Reference

Tool	Description
browser_navigate	Navigate to URL
browser_click	Click element by selector
browser_type	Type text into input
browser_select_option	Select dropdown option
browser_get_text	Get text content
browser_evaluate	Execute JavaScript
browser_snapshot	Get accessible page snapshot
browser_close	Close browser context
browser_choose_file	Upload file
browser_press	Press keyboard key

Configuration Options

# Security
--allowed-hosts example.com,api.example.com
--blocked-origins malicious.com
--ignore-https-errors

# Browser settings
--browser chromium|firefox|webkit
--headless
--viewport-size 1920x1080
--user-agent "Custom Agent"

# Timeouts
--timeout-action 10000      # Action timeout (ms)
--timeout-navigation 30000  # Navigation timeout (ms)

# Output
--output-dir ./playwright-output
--save-trace
--save-video 1280x720

Examples

Login to Website

browser_navigate: { url: "https://example.com/login" }
browser_type: { selector: "#username", text: "user" }
browser_type: { selector: "#password", text: "pass" }
browser_click: { selector: "#submit" }
browser_get_text: { selector: ".welcome-message" }

Extract Table Data

browser_navigate: { url: "https://example.com/data" }
browser_evaluate: { 
  script: "() => { return Array.from(document.querySelectorAll('table tr')).map(r => r.textContent); }" 
}

Screenshot

browser_navigate: { url: "https://example.com" }
browser_evaluate: { script: "() => { document.body.style.zoom = 1; return true; }" }
# Screenshot saved via --output-dir or returned in response

Security Notes

• By default restricts file system access to workspace root
• Host validation prevents navigation to untrusted domains
• Sandboxing enabled by default (use --no-sandbox with caution)
• Service workers blocked by default

Troubleshooting

# Update browsers
npx playwright install chromium

# Debug mode
npx @playwright/mcp --headless=false --output-mode=stdout

# Check installation
playwright-mcp --version

Links

• Playwright Docs
• MCP Protocol
• NPM Package