Skip to main content
MCP server CX Codex

Bright Data · docker — Claude Code MCP server: what it does, how to install

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.

no license updated 2026-10-29

Open on GitHub

What Bright Data does

The MCP server connects coding assistants directly to live internet resources. Instead of replying with stale training data, agents navigate target sites, crawl pages, and collect structured public information.

Bright Data routes requests through its infrastructure to stop anti-scraping barriers. This prevents sudden IP rate limits or intrusive CAPTCHA challenges during automated browsing tasks.

The server relies entirely on external network availability to fetch public pages on demand.

What it helps with

  • extract structured data from public web pages
  • bypass IP rate limits and CAPTCHA screens
  • retrieve real-time internet data instead of stale knowledge
  • crawl target websites across public URLs

Example prompts for the agent

  • Search this public site for recent release notes and pull the changelog
  • Crawl the target documentation page and extract all code snippets
  • Navigate to the public article URL and extract the plain content

How to install Bright Data

Install

The MCP registry has no launch command for it: see the repository README

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

What does the Bright Data MCP server do?

It provides AI assistants with live web access to search, crawl, and extract structured data from public sites. The service handles traffic so requests avoid CAPTCHAs and rate limits.

Which platforms support this MCP server?

It works with Claude Code, Cursor, Codex, GitHub Copilot, Windsurf, Cline, Zed, and Gemini CLI.

How does the server avoid rate limits?

The server routes network traffic through Bright Data's platform, shielding the AI assistant from anti-bot challenges and IP bans.

Similar MCP servers

All MCP servers for Browser and scraping →

Bright Data by other authors comes first.

Bright Data brightdata 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. CX Codex +1 300installs 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 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 data-feeds davila7 data-feeds — a Claude Code skill that pulls structured JSON from 40+ websites via Bright Data's Web Data API with automatic polling. Cover e-commerce, social platforms, job networks, and real estate — just pass a URL. CX Codex +1 816installs scrape brightdata This skill helps an agent collect structured website data and choose between a ready scraper, Scraper Studio, or fetch for a one-off page. CX Codex +1 11,100installs scrapy-web-scraping Mindrally scrapy-web-scraping — a skill for Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, and OpenCode that teaches agents to build Scrapy spiders, configure pipelines, and handle anti-bot measures. CX Codex +1 2,100installs firecrawl Firecrawl Skills to search, scrape, crawl, and map websites directly using the Firecrawl CLI inside agent sessions. CX Codex ★ 1,596repo stars

Project sponsors

Companies that keep this analytics open