Pricing

Rating

Developer

Actor stats

Categories

Share

Playwright MCP Server

Give your AI agents a real browser. This MCP server runs Playwright on Apify's infrastructure, letting AI agents navigate websites, fill forms, click buttons, extract data, and take screenshots — all through the Model Context Protocol.

Why Use This?

• No local browser needed — runs on Apify's cloud with anti-blocking proxies
• 16 browser tools — navigate, click, type, screenshot, extract text/HTML, run JavaScript, and more
• Anti-blocking built in — Apify proxy infrastructure handles CAPTCHAs and blocks
• Works with any MCP client — Claude, OpenAI, custom agents via SSE or HTTP transport

Available Tools (16)

Quick Start

Connect via MCP (SSE)

{
"mcpServers":{
"playwright":{
"url":"https://nexgendata--playwright-mcp-server.apify.actor/sse",
"transport":"sse",
"headers":{
"Authorization":"Bearer YOUR_APIFY_API_TOKEN"
}
}
}
}

Connect via HTTP

{
"mcpServers":{
"playwright":{
"url":"https://nexgendata--playwright-mcp-server.apify.actor/mcp",
"transport":"http"
}
}
}

Use Cases

• Web research agents — Browse and extract data from any website
• Form automation — Fill out applications, surveys, registrations
• Testing & monitoring — Check website functionality and content
• Data extraction — Scrape dynamic JavaScript-rendered pages
• Screenshot capture — Visual documentation and monitoring
• Price monitoring — Track prices across e-commerce sites

Example: Navigate and Extract

Agent: "Go to example.com and get all the links"
Tool calls:
1. navigate(url="https://example.com")
2. get_links()

Example: Fill a Form

Agent: "Search for 'web scraping' on Google"
Tool calls:
1. navigate(url="https://google.com")
2. type(selector="textarea[name='q']", text="web scraping", pressEnter=true)
3. wait(selector="#search")
4. get_text(selector="#search")

Proxy Support

Enable Apify proxy for anti-blocking:

{
"proxyConfiguration":{
"useApifyProxy":true
}
}

Pricing

Pay per browser action via Apify's pay-per-event model:

• Session start: $0.05
• Per tool call: $0.01

Support

Questions? Open an issue on the actor page or contact NexGenData.

💻 Code Example — Python

from apify_client import ApifyClient
client = ApifyClient("YOUR_APIFY_TOKEN")
run = client.actor("nexgendata/playwright-mcp-server").call(run_input={
# Fill in the input shape from the actor's input_schema
})
for item in client.dataset(run["defaultDatasetId"]).iterate_items():
print(item)

🌐 Code Example — cURL

curl-X POST "https://api.apify.com/v2/acts/nexgendata~playwright-mcp-server/run-sync-get-dataset-items?token=YOUR_TOKEN"\
-H"Content-Type: application/json"\
-d'{ /* input schema */ }'

❓ FAQ

Q: How do I get started? Sign up at apify.com, grab your API token from Settings → Integrations, and run the actor via the Apify console, API, Python SDK, or any integration (Zapier, Make.com, n8n).

Q: What's the typical cost per run? See the pricing section below. Most runs finish under $0.10 for typical batches.

Q: Is this actor maintained? Yes. NexGenData maintains 165+ Apify actors and ships updates regularly. Bug reports via the Apify console issues tab get responses within 24 hours.

Q: Can I use the output commercially? Yes — you own the output data. Check the target site's Terms of Service for any usage restrictions on the scraped content itself.

Q: How do I handle rate limits? Apify manages concurrency and retries automatically. For very large batches (10K+ items), run multiple smaller jobs in parallel instead of one mega-job for better reliability.

💰 Pricing

Pay-per-event pricing — you only pay for what you actually extract.

• Actor Start: $0.0050
• tool call: $0.0050

🔗 Related NexGenData Actors

• RAG Web Browser
• AI Web Scraper
• Hacker News Scraper

🚀 Apify Affiliate Program

New to Apify? Sign up with our referral link — you get free platform credits on signup, and you help fund the maintenance of this actor fleet.

📚 More From NexGenData

Explore the full catalog, tutorials, Gumroad data packs, and newsletter at thenextgennexus.com — the brand home for everything we ship.

• 📖 Tutorials & how-to guides
• 🗂️ Full actor catalog with usage examples
• 📦 Gumroad data packs (one-time purchases)
• 📬 Newsletter — monthly drops of new actors and revenue experiments

Built and maintained by NexGenData — 165+ actors covering scraping, enrichment, MCP servers, and automation. 🏠 Home: thenextgennexus.com

Why Playwright MCP Beats Browserbase, Anthropic Computer Use API, Selenium Grid & Generic LLMs

Most teams pick this MCP server because it is cheaper than Browserbase for low-volume agent traffic, works with any MCP client (not just Claude) unlike Anthropic Computer Use, and ships pre-baked Apify proxy + captcha handling that Selenium Grid forces you to build yourself. A drop-in browser tool for any AI agent that needs to load a page, click, fill, and screenshot.

Related NexGenData MCP Servers & Web-Scraping Actors

Browse the full NexGenData catalog of 260+ actors at https://apify.com/nexgendata?fpr=2ayu9b

💰 Pricing Example

This actor uses Pay-Per-Event pricing — you only pay for results.

• Typical run (small): 100 results × $0.05 = $5.00
• Medium run: 500 results × $0.05 = $25.00
• Large run (power user): 2,000 results × $0.05 = $100.00

Free Apify accounts get $5/mo in platform credit. A typical browser automation tooling workflow at this scale typically exceeds the free credit — upgrade to a paid Apify plan for unrestricted use.

🔗 Related Actors

Pair with these for a complete workflow:

• 🕷️ Web Scraping MCP — AI Content Extraction — MCP server bundling HTTP + parsing tools for AI agents
• 🔧 Dev Tools MCP — AI Code & Package Search — MCP server bundling dev + DevOps tools for AI agents
• 🌐 Domain Intel MCP — AI WHOIS & DNS Analysis — MCP server for DNS, WHOIS, and domain-history lookups
• 🔍 SEO MCP — AI Website Auditing & Analysis — MCP server bundling 15+ SEO + web-perf tools

⭐ Found this useful?

If this Actor saved you time, a quick review on the Apify Store genuinely helps other teams discover it. Have a feature request or hit a problem? Open it from the Issues tab — we read every one.