ScrapeLab MCP

The most complete stealth browser MCP server for AI agents.

84 tools. Undetectable by anti-bot systems. Full CDP access.
LLM-ready markdown. Auto cookie consent dismiss (100+ CMPs).
Accessibility snapshots, PDF export, HAR capture, network hooks, element cloning.

What is this?

An MCP server that gives AI agents (Claude, Cursor, Windsurf, etc.) a fully undetectable browser with 84 automation tools. Built on nodriver + Chrome DevTools Protocol + FastMCP.

Why not Playwright MCP? Playwright is detectable. Sites with Cloudflare, DataDome, or any anti-bot system will block it. ScrapeLab uses nodriver (the successor of undetected-chromedriver) — no navigator.webdriver flag, no automation fingerprints, no detection.

Key differentiators

LLM-Ready Markdown

get_page_content returns clean markdown instead of raw HTML — 98-99% smaller, ready for LLM consumption.

Both modes strip scripts, styles, SVGs, cookie banners, navigation chrome, and HTML comments before conversion.

Cookie Consent Auto-Dismiss

Every navigate call automatically dismisses cookie/GDPR consent popups. No manual clicks, no leftover overlays blocking your scraper.

Three-layer system:

1. DuckDuckGo autoconsent — 2863 rules covering 100+ consent management platforms (iubenda, Cookiebot, OneTrust, Quantcast, TrustArc, etc.)
2. CMP JS API fallback — Calls platform APIs directly from the main page (_sp_.destroyMessages(), OneTrust.AllowAll(), __tcfapi, Didomi, Cookiebot) — handles cross-origin iframe popups like SourcePoint
3. DOM click fallback — Catches multi-step consent flows (e.g. iubenda's 2-click Italian flow) by re-clicking accept buttons

Disable per-instance with spawn_browser(auto_dismiss_consent=False).

Quickstart

1. Clone and install

git clone https://github.com/competitorch/ScrapeLabMCP.git
cd ScrapeLabMCP
python -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt

2. Add to your MCP client

Claude Desktop (claude_desktop_config.json):

{
  "mcpServers": {
    "scrapelab-mcp": {
      "command": "/path/to/ScrapeLabMCP/.venv/bin/python",
      "args": ["/path/to/ScrapeLabMCP/src/server.py"]
    }
  }
}

Claude Code CLI:

claude mcp add-json scrapelab-mcp '{
  "type": "stdio",
  "command": "/path/to/.venv/bin/python",
  "args": ["/path/to/src/server.py"]
}'

3. Use it

You: "Open a browser and navigate to example.com"
You: "Take a screenshot and get the accessibility snapshot"
You: "Get the page content as markdown"
You: "Export the page as PDF"
You: "Show me all network requests and export as HAR"

Tools Reference (84 tools)

Browser Management (10 tools)

Element Interaction (11 tools)

Element Extraction (8 tools)

Deep extraction with optional save_to_file=True on every tool.
Style extraction supports method="js" or method="cdp" for maximum accuracy.

Progressive Cloning (10 tools)

Lazy-load element data on demand — start lightweight, expand what you need.

Network & Traffic (12 tools)

Deep network monitoring with interception, search, and standard export formats.

Dynamic Hooks (7 tools)

AI-generated Python functions that intercept and modify network traffic in real-time.

CDP Functions (12 tools)

Direct Chrome DevTools Protocol access for advanced automation.

Cookies & Storage (3 tools)

Tab Management (5 tools)

Debugging (5 tools)

Modular Architecture

Load only what you need:

# Full suite (84 tools)
python src/server.py

# Core only — browser + element interaction
python src/server.py --minimal

# Disable specific sections
python src/server.py --disable-cdp-functions --disable-progressive-cloning

# List all sections
python src/server.py --list-sections

Sections

Environment Variables

Troubleshooting

No compatible browser found — Install Chrome, Chromium, or Edge. Run validate_browser_environment_tool() to diagnose.

Too many tools for your use case — Use --minimal or --disable-<section>.

Browser instances piling up — Instances auto-close after 5 minutes of inactivity (configurable via SCRAPELAB_IDLE_TIMEOUT).

License

MIT — see LICENSE.