brightdata-web-mcp

# Bright Data Web MCP

Use this skill for **reliable web access** in MCP-compatible agents. Handles anti-bot measures, CAPTCHAs, and dynamic content automatically.

## Quick Start

### Search the web

```
Tool: search_engine
Input: { "query": "latest AI news", "engine": "google" }
```

Returns JSON for Google, Markdown for Bing/Yandex. Use `cursor` parameter for pagination.

### Scrape a page to Markdown

```
Tool: scrape_as_markdown
Input: { "url": "https://example.com/article" }
```

### Extract structured data (Pro/advanced_scraping)

```
Tool: extract
Input: { 
  "url": "https://example.com/product",
  "prompt": "Extract: name, price, description, availability"
}
```

## When to Use

| Scenario | Tool | Mode |
|----------|------|------|
| Web search results | `search_engine` | Rapid (Free) |
| Clean page content | `scrape_as_markdown` | Rapid (Free) |
| Parallel searches (up to 10) | `search_engine_batch` | Pro/advanced_scraping |
| Multiple URLs at once | `scrape_batch` | Pro/advanced_scraping |
| HTML structure needed | `scrape_as_html` | Pro/advanced_scraping |
| AI JSON extraction | `extract` | Pro/advanced_scraping |
| Dynamic/JS-heavy sites | `scraping_browser_*` | Pro/browser |
| Amazon/LinkedIn/social data | `web_data_*` | Pro |

## Setup

**Remote (recommended) - No installation required:**

SSE Endpoint:
```
https://mcp.brightdata.com/sse?token=YOUR_API_TOKEN
```

Streamable HTTP Endpoint:
```
https://mcp.brightdata.com/mcp?token=YOUR_API_TOKEN
```

**Local:**
```bash
API_TOKEN=<token> npx @brightdata/mcp
```

## Modes & Configuration

### Rapid Mode (Free - Default)
- **5,000 requests/month free**
- Tools: `search_engine`, `scrape_as_markdown`

### Pro Mode
- All Rapid tools + 60+ advanced tools
- Remote: add `&pro=1` to URL
- Local: set `PRO_MODE=true`

### Tool Groups
Select specific tool bundles instead of all Pro tools:
- Remote: `&groups=ecommerce,social`
- Local: `GROU