brightdata-mcp MCP server

A powerful Model Context Protocol (MCP) server that provides an all-in-one solution for public web access.

What brightdata-mcp does

Summarised from the project README; check the repository for the latest details.

Tools exposed (20+)

• search_engine – Search Google, Bing, or Yandex. Google returns JSON (URL, title, description); Bing and Yandex return Markdown. Paginate with the `cursor` p
• search_engine_batch – Up to 10 search queries in one call
• scrape_as_markdown – Any URL as Markdown. Bot protection and CAPTCHA handled automatically
• scrape_batch – Up to 10 URLs in one call; returns an array of URL/content pairs in Markdown
• discover – AI-relevance-ranked web search. Returns scored results (title, description, URL, relevance score). Supports intent-based ranking, geo-target
• scrape_as_html – Any URL as raw HTML
• extract – Scrape a page and convert it to structured JSON using AI, with an optional custom extraction prompt
• session_stats – Tool usage counts for the current session
• search_scrapers – Find scrapers by site or data type (e.g. "amazon reviews", "linkedin.com"). Returns dataset ID, name, domain and collection methods
• get_scraper_details – Description, input fields, example input and main output fields for one scraper method
• run_scraper – Run a scraper method. Waits up to 45 seconds; if still running, returns a `snapshotid` to check later
• get_scraper_progress – Status of a run: starting, running, ready, failed or canceled
• get_scraper_results – Records of a finished run
• refresh_scrapers – Reload the scraper list now instead of waiting for the daily refresh
• scraping_browser_navigate – Open or reuse a browser session and navigate to a URL
• scraping_browser_go_back – Navigate back
• scraping_browser_go_forward – Navigate forward
• scraping_browser_snapshot – ARIA snapshot of the page listing interactive elements with refs. Required before ref-based actions
• scraping_browser_click_ref – Click an element by ref from the latest snapshot
• scraping_browser_type_ref – Type into an element by ref; optionally press Enter to submit

Requirements

• Node.js (runs with npx)
• Environment variables: API_TOKEN

How to install brightdata-mcp MCP in Claude Desktop, Cursor and VS Code

claude mcp add --env 'API_TOKEN=<your-api-token-here>' --transport stdio Bright-Data -- npx @brightdata/mcp

{
  "mcpServers": {
    "Bright Data": {
      "command": "npx",
      "args": [
        "@brightdata/mcp"
      ],
      "env": {
        "API_TOKEN": "<your-api-token-here>"
      }
    }
  }
}

{
  "mcpServers": {
    "Bright Data": {
      "command": "npx",
      "args": [
        "@brightdata/mcp"
      ],
      "env": {
        "API_TOKEN": "<your-api-token-here>"
      }
    }
  }
}

{
  "servers": {
    "Bright Data": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "@brightdata/mcp"
      ],
      "env": {
        "API_TOKEN": "<your-api-token-here>"
      }
    }
  }
}

Add to config generator – combine it with other servers, or get the Windsurf format.

Featured in: Best MCP servers for web scraping · Best MCP servers for browser automation · Best MCP servers for data analysis

Listed on Socketlist – add this badge to your README:

Badge markdown[](https://socketlist.pages.dev/s/brightdata-brightdata-mcp/)

Maintain this project? Get it featured for free during launch →

Compare with chrome-devtools-mcp →

Related Browser Automation MCP servers