Skip to main content
MCP server CX Codex

Bright Data · brightdata — Claude Code MCP server: search and scrape

Bright Data — a hosted MCP server that gives coding agents Google, Bing and Yandex search plus page-to-Markdown scraping. Handy when the agent needs live web content.

no license 300 installs updated 2025-04-16

Install into Claude Code · Platform CLI: remote server All methods and platforms ↓
claude mcp add --transport http brightdata https://brightdata.run.tools
Open on GitHub

What Bright Data does

The server lives at https://brightdata.run.tools, so there is nothing to run on your machine. Four tools come with it: search_engine returns SERP results from Google, Bing or Yandex, scrape_as_markdown converts a single page to Markdown, and the two batch variants repeat that for several queries or URLs in one call.

Per the author, pages that use bot detection or CAPTCHA still come back as Markdown. Every fetch happens on Bright Data's side, which means the content of each page you ask for leaves your machine through that endpoint. Internal pages behind a login are a poor fit for exactly that reason.

Setup in Claude is one line: claude mcp add --transport http brightdata https://brightdata.run.tools. The author offers the server for free.

What it helps with

  • pull live SERP results into an agent's context
  • read a page that blocks bots as plain Markdown
  • scrape a list of URLs in one batch call
  • compare results across Google and Yandex
  • fetch current news while editing code

Example prompts for the agent

  • Search Google for recent MCP posts with search_engine and save the top five to notes.md.
  • Scrape the competitor's pricing page with scrape_as_markdown and list the tiers.
  • Run search_engine_batch on "n8n webhook" and "n8n cron" and put both result sets in one table.

How to install Bright Data

Platform CLI: remote server

claude mcp add --transport http brightdata https://brightdata.run.tools

Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more

Questions about Bright Data

How do I install Bright Data in Claude Code?

Run claude mcp add --transport http brightdata https://brightdata.run.tools.

What does Bright Data do?

It hands the agent web search across Google, Bing and Yandex, plus scraping of one page or many into Markdown, all through a hosted endpoint.

Which search engines does search_engine cover?

Google, Bing and Yandex. search_engine_batch returns JSON for Google and Markdown for the other two.

Similar MCP servers

All MCP servers for Browser and scraping →

Bright Data by other authors comes first.

Bright Data docker The Bright Data MCP server connects AI assistants to the live web. It searches, crawls, and extracts data from public websites while avoiding CAPTCHAs and rate limits. CX Codex +1 Keenable Web Search keenable Keenable Web Search — a remote MCP server for searching the web and retrieving page contents as markdown. Runs out of the box without API keys or accounts. CX Codex +1 2,498installs bright-data-mcp Bright Data This skill routes every web data task in Claude through the Bright Data MCP server instead of the built-in WebFetch and WebSearch. Useful when pages block bots or you want clean JSON. CX Codex +1 722installs bright-data-best-practices brightdata bright-data-best-practices — a reference skill that teaches a coding assistant which Bright Data API fits the task and how to wire it up. Handy when the agent builds a scraper or a bdata wrapper. CX Codex +1 1,800installs tavily-search tavily-ai tavily-search — a skill for Claude Code that enables web searching and data extraction from webpages. Use it to verify facts, read current news, and gather information beyond the model's training data. CX Codex +1 39,400installs Exa Search exa Exa Search searches the web and converts live web pages into clean markdown for AI assistants. Helpful when fetching fresh documentation for third-party libraries and APIs. CX Codex +1 9,181installs web-content-fetcher shirenchuang web-content-fetcher takes a URL and returns the page's main content as clean Markdown, keeping headings, links, images, lists and code blocks. Handy when you want an article or docs page read inside the chat. CX Codex +1 3,000installs

Project sponsors

Companies that keep this analytics open