Playwright MCP Browser

Run a real Chrome browser as an MCP-native tool so AI agents can browse, interact with, and extract data from modern websites — without writing custom scrapers.

Extract structured data from a live website in real time using MCP

What this Actor is

Run a real browser from an AI agent to extract data from any website — no scraper code required.

Under the hood, this exposes a Playwright browser as an MCP tool.

It lets agents:

• load real websites (including JavaScript-heavy pages)
• interact with elements (click, scroll, fill, etc.)
• extract structured data, text, links, and metadata
• capture screenshots

All through a simple MCP interface.

---

How it works (in 3 steps)

1. Give your agent a prompt (e.g., “extract all product listings”)
2. The browser navigates and interacts with the page
3. You get structured JSON back

No selectors. No scripts. No maintenance.

---

Why use this Actor

Use this when you want scraping workflows using natural language.

Key advantages

• No scraper code required — works with natural language agents
• Handles JavaScript-heavy sites automatically
• Unified extraction (text, HTML, links, structured data)
• Works with MCP-compatible agents (OpenCode, Claude Code, etc.)
• Runs on Apify → scheduling, storage, APIs, proxies

---

The shift

Traditional scraping:

• Write selectors
• Handle JS rendering
• Maintain scripts

This Actor:

• Describe what you want
• Get structured data

That’s it.

---

Best for

• AI agents that need browser access to websites
• Extracting data from dynamic or JS-heavy pages
• Research and content extraction workflows
• QA and page inspection automation
• Rapid prototyping of scraping pipelines

Not for

• Logging into websites or managing sessions
• Scraping behind authentication walls
• File downloads/uploads
• Full-scale crawling jobs (use Apify crawlers instead)

---

Example workflows

1. Competitive price monitoring

• Navigate to product listing pages
• Auto-detect item structure
• Extract name, price, rating, URL
• Paginate and repeat
• Store structured dataset

Output:

[{ "name": "Widget Pro", "price": 29.99, "url": "https://..." }]

---

2. E-commerce QA automation

• Load product or checkout pages
• Click buttons, test inputs, navigate flows
• Extract links and metadata
• Capture before/after screenshots

Output:

• Pass/fail validation + screenshots per step

---

3. Job posting aggregator

• Search job boards (LinkedIn, Indeed, etc.)
• Detect job card structure automatically
• Extract title, company, location, salary, URL
• Combine results across multiple sources

Output:

• Unified dataset across job platforms

---

Prompt examples (copy & run)

Turn any page into structured data

Go to [URL], detect repeating items, and return name, price, and URL as JSON.

Extract all visible text from a page

Go to https://scrapethissite.com and extract all visible text, page title, and links.

Extract product listings

Go to https://web-scraping.dev/products and extract all products with name, price, and URL. Return structured JSON.

Scrape multiple pages

Go to https://web-scraping.dev/products, extract all product listings, then click next page and repeat until there are no more pages.

Extract specific section

Go to https://scrapingtest.com and extract only the main content area, including headings and paragraphs.

Aggregate job listings

Search for 'software engineer' on Indeed, extract job title, company, location, and URL, then repeat for multiple pages.

Test page interactions

Go to https://scrapethissite.com, click all main navigation links, take screenshots of each page, and report any broken links.

Extract metadata

Go to https://scrapethissite.com and extract title, meta description, OpenGraph tags, and all links.

Auto-detect structure and extract

Go to https://scrapingsandbox.com, detect repeating item structure, and extract structured data for each item.

---

Starter workflows

Competitive price monitoring

1. Go to competitor product listing page
2. Wait for full page load
3. Detect repeating product structure
4. Extract name, price, rating, and URL
5. Click "Next page" if available
6. Repeat until pagination ends
7. Store results in dataset
8. Capture screenshot for verification

Use case:

• Track competitor pricing over time
• Feed into analytics or alerts

Job board aggregator

1. Go to job board (Indeed, LinkedIn, etc.)
2. Search for target role (e.g., "marketing manager")
3. Wait for results to load
4. Detect job listing structure
5. Extract title, company, location, and URL
6. Paginate through results
7. Repeat for multiple job boards
8. Combine into a unified dataset

Use case:

• Build lead lists from hiring signals
• Identify companies actively hiring

Website QA automation

1. Load target page
2. Capture baseline screenshot
3. Click all major navigation elements
4. Test forms and inputs
5. Extract all links
6. Identify broken links or missing metadata
7. Capture screenshots of each state
8. Output pass/fail report

Use case:

• Automated regression testing
• SEO validation

Content extraction pipeline

1. Go to target article or blog page
2. Extract main content (headings + paragraphs)
3. Extract metadata (title, description)
4. Extract all outbound links
5. Repeat for multiple URLs
6. Store structured content in dataset

Use case:

• Build datasets for AI training
• Content aggregation pipelines

Multi-site research

1. Search Google or navigate to known sources
2. Open multiple tabs
3. Extract key content from each page
4. Summarize or compare results
5. Store findings

Use case:

• Competitive research
• Market analysis

Recommended agent system prompt

"You are a web automation agent using a browser. Navigate pages, interact when needed, and extract structured data. Prefer structured extraction when possible. Minimize unnecessary interactions."

---

Input

Configure defaults in the Input tab:

{
    "headless": true,
    "respectRobotsTxt": true,
    "userAgent": "ApifyPlaywrightMcp/1.0 (+https://apify.com)",
    "viewportWidth": 1280,
    "viewportHeight": 720,
    "globalTimeoutMillis": 30000,
    "concurrencyMode": "serialized"
}

Only http and https URLs are supported.

---

Output

All responses are returned via MCP tool calls as structured JSON.

Example: page.extract

{
    "ok": true,
    "result": {
        "text": "Example Domain...",
        "links": [{ "text": "Learn more", "href": "https://iana.org/domains/example" }],
        "metadata": {
            "title": "Example Domain"
        }
    },
    "context": {
        "url": "https://example.com/"
    }
}

---

Pricing

Pay-per-event + Apify compute.

Event	When charged	Price
browser-session	Browser session created	$0.005
page-loaded	Page successfully loaded	$0.002
data-operation	Extraction succeeds	$0.003
interaction	Click, fill, scroll, etc.	$0.001
screenshot	Screenshot captured	$0.001

Typical cost

Simple workflow:

• Load page → $0.002
• Extract data → $0.003

≈ $0.005 per page

---

Common patterns

Extract only what you need

Use targeted extraction:

{
    "include": {
        "text": true,
        "links": true
    }
}

---

Structured extraction

{
    "include": {
        "structured": {
            "enabled": true,
            "schema": {
                "type": "array",
                "itemSelector": ".product",
                "fields": {
                    "name": { "selector": ".name" },
                    "price": { "selector": ".price" }
                }
            }
        }
    }
}

---

Auto-discover structure

Use:

page.infer_structure

Then pass the schema into page.extract.

---

Limitations

This Actor is intentionally scoped for public-web browsing.

It does not support:

• authentication or login flows
• credential storage
• CAPTCHA solving
• file uploads/downloads
• session persistence

---

How this compares

If you’ve ever written a scraper just to grab data from one page — this replaces that entire workflow.

Tool	When to use
This Actor	MCP-based browsing + extraction
Playwright (raw)	Full custom scripting
Apify Crawlers	Large-scale crawling jobs
Scraping APIs	Simple static extraction

---

Advanced usage

• Multi-tab browsing per session
• Screenshots saved to key-value store
• Schema-driven extraction
• DNS allowlists for security
• Custom Chrome binaries

---

Roadmap

This Actor is the foundation for a broader MCP-native browser ecosystem.

Planned areas of expansion:

• Authenticated browsing (login/session support)
• Advanced interaction flows (multi-step automation)
• Domain-specific extraction presets
• Higher-level workflows built on top of MCP primitives

The current version is intentionally scoped for reliable public-web extraction.

---

Support

• Use the Issues tab for bugs and requests
• Designed for extension into a full browser MCP ecosystem

---

Disclaimer

Only scrape data you are allowed to access. Respect site terms, robots.txt, and applicable laws.