# Bright Data (verified)

One (free) MCP for the Web. Easily search, crawl, navigate, and extract websites without getting blocked. Ideal for discovering and retrieving structured insights from any public source - effortlessl…

## Quick Start

```bash
# Connect this server (installs CLI if needed)
npx -y @smithery/cli@latest mcp add brightdata

# Browse available tools
npx -y @smithery/cli@latest tool list brightdata

# Get full schema for a tool
npx -y @smithery/cli@latest tool get brightdata search_engine

# Call a tool
npx -y @smithery/cli@latest tool call brightdata search_engine '{}'
```

## Direct MCP Connection

Endpoint: `https://brightdata.run.tools`

**Required config:**
- `token` (query) — Bright Data API Token

**Optional config:**
- `pro` (query) — Enables Pro mode when set to 1. This unlocks Bright Data MCP’s full extended toolset.
- `tools` (query) — Lets you list specific tool names by their identifiers to expose only those tools you need.
- `groups` (query) — Specifies one or more tool group IDs (e.g., ecommerce) to expose curated bundles of tools.
- `browser` (query) — Uses a custom “browser” zone name instead of the default for browser automation workloads.
- `unlocker` (query) — Uses a custom “unlocker” zone name instead of the default.

## Tools (4)

- `search_engine` — Scrape search results from Google, Bing or Yandex. Returns SERP results in JSON or Markdown (URL, title, description), …
- `scrape_as_markdown` — Scrape a single webpage URL with advanced options for content extraction and get back the results in MarkDown language.…
- `search_engine_batch` — Run multiple search queries simultaneously. Returns JSON for Google, Markdown for Bing/Yandex.
- `scrape_batch` — Scrape multiple webpages URLs with advanced options for content extraction and get back the results in MarkDown languag…

```bash
# Get full input/output schema for a tool
npx -y @smithery/cli@latest tool get brightdata <tool-name>
```

---

Source: https://github.com/brightdata/brightdata-mcp-sse | License: MIT