MCP Connector

Access Web Data and Automate Browsers

Give AI real-time web access: search, scrape any page to markdown, browser automation, and 60+ structured data tools without getting blocked.


91
Spark score
out of 100
Updated last month
Version 2.11.0
Models
universal

Add to Favorites

Why it matters

Empower AI agents to access public web data and automate browser interactions without encountering blocks. This connector facilitates web scraping, searching, and browser automation for AI-driven tasks.

Outcomes

What it gets done

01

Scrape web pages and extract content as clean markdown.

02

Perform web searches with AI-optimized results.

03

Automate browser actions for complex web interactions.

04

Bypass anti-blocking measures for reliable web access.

Install

Add it to your toolbox

Run in your project directory:

curl -fsSL https://spark.entire.vc/get/vb-brightdata | bash

Capabilities

Tools your agent gets

search_engine

Web search with AI-optimized results

scrape_as_markdown

Convert any webpage to clean markdown

Overview

Bright Data MCP

Bright Data's MCP server for real-time web access - AI-optimized search, markdown scraping, browser automation, and 60+ structured data tools across e-commerce, social, finance, and more. Reach for this when an AI agent needs current web information or reliable, unblockable scraping - free tier covers basic search/scrape, Pro mode unlocks the full structured-data toolset.

What it does

Bright Data's Web MCP connects AI assistants to the live web without getting blocked, rate-limited, or served CAPTCHAs. The default (Rapid) mode provides three base tools: search_engine (AI-optimized web search), scrape_as_markdown (convert any webpage to clean markdown), and discover (AI-ranked search with intent-based relevance scoring for deep research and RAG pipelines).

Pro mode unlocks 60+ additional tools organized into groups: ecommerce (Amazon, Walmart, Google Shopping product data), social (LinkedIn, TikTok, YouTube), browser (full Scraping Browser automation - snapshot, click, screenshot), finance (Yahoo Finance), business (Crunchbase, ZoomInfo, Zillow), research (GitHub, Reuters), app_stores (Google Play, Apple App Store), travel (Booking.com), geo (ChatGPT/Grok/Perplexity AI brand-visibility insights), code (npm and PyPI package metadata for coding agents), and advanced_scraping (batch search/scrape and AI-assisted extraction).

npx @brightdata/mcp

When to use - and when NOT to

Use this when an AI assistant needs current, real-world information the model wasn't trained on - stock prices, restaurant ratings, weather, trending topics, or the latest npm/PyPI package version and README - or when building agents that need reliable, unblockable web scraping and browser automation.

Do NOT expect Pro-mode tools (browser control, most web_data_* APIs) on the free tier: the free Rapid mode only includes search_engine, scrape_as_markdown, and discover. The free tier grants 5,000 credits/month (no credit card required, ~$7.50 value, does not roll over) - base tools cost 1 credit per request, web_data_* tools cost 1 credit per record returned. Pro mode is billed separately and is not included in the free tier.

Capabilities

  • Rapid mode (free): search_engine, scrape_as_markdown, discover
  • Pro mode (60+ tools): browser automation (scraping_browser.*), structured web data extraction (web_data_*) across e-commerce, social media, finance, business/location intelligence, research/news, app stores, and travel
  • GEO tools: query ChatGPT, Grok, and Perplexity directly for AI brand-visibility insights
  • Code tools: npm and PyPI package versions, READMEs, and metadata for coding agents
  • Custom tool selection via GROUPS and TOOLS environment variables

How to install

Hosted, zero-install option - add this URL to your MCP client: https://mcp.brightdata.com/mcp?token=YOUR_API_TOKEN. Or run locally:

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

Enable Pro mode with "PRO_MODE": "true", or select specific tool groups with "GROUPS": "browser,advanced_scraping" and "TOOLS": "extract".

Who it's for

Developers building AI agents, coding assistants, or research/market-intelligence tools that need reliable, unblockable real-time web access - from simple search and scraping to structured e-commerce, social, and financial data extraction.

Source README
Bright Data Logo

The Web MCP

๐ŸŒ Give your AI real-time web superpowers
Seamlessly connect LLMs to the live web without getting blocked

npm version npm downloads License

Quick Start โ€ข Features โ€ข Pricing โ€ข Demos โ€ข Docs โ€ข Support

๐ŸŽ‰ Free Tier Available! ๐ŸŽ‰

5,000 credits/month FREE
No credit card required ยท Auto-renews monthly ยท Perfect for prototyping and everyday AI workflows


NEW: Code Tool group - Your Coding Agent's Best Friend

Instant access to npm and PyPI package data, right from your AI agent.

Need the latest version of a package? Want to read its README without leaving your workflow?
The Code tool group gives coding agents structured, reliable package metadata on demand -
no scraping, no stale caches, just the data your agent needs to make smart dependency decisions.

npm
Package versions, READMEs, metadata & dependencies
PyPI
Python package info, versions & project details

GROUPS="code"  ยท  The go-to tool for Claude Code, Cursor, Windsurf & any MCP-powered coding agent

GEO & AI Brand Visibility Tools

See how ChatGPT, Grok, and Perplexity talk about your brand.

Query leading LLMs directly from your agent and get back structured, markdown-formatted answers.
The ultimate feedback loop for Generative Engine Optimization (GEO) - monitor AI-generated recommendations, track brand mentions across LLMs, and understand how AI perceives your products.

ChatGPT
AI-generated insights, citations & recommendations
Grok
Real-time AI analysis powered by X data
Perplexity
Search-augmented AI answers with sources

GROUPS="geo"  ยท  Works with any MCP-compatible agent


๐ŸŒŸ Overview

The Web MCP is your gateway to giving AI assistants true web capabilities. No more outdated responses, no more "I can't access real-time information" - just seamless, reliable web access that actually works.

Built by Bright Data, the world's #1 web data platform, this MCP server ensures your AI never gets blocked, rate-limited, or served CAPTCHAs.

โœ… Works with Any LLM
Claude, GPT, Gemini, Llama
๐Ÿ›ก๏ธ Never Gets Blocked
Enterprise-grade unblocking
๐Ÿš€ 5,000 Free Credits
Monthly ยท No card needed
โšก Zero Config
Works out of the box

๐ŸŽฏ Perfect For

  • ๐Ÿ” Real-time Research - Get current prices, news, and live data
  • ๐Ÿ›๏ธ E-commerce Intelligence - Monitor products, prices, and availability
  • ๐Ÿ“Š Market Analysis - Track competitors and industry trends
  • ๐Ÿค– AI Agents - Build agents that can actually browse the web
  • ๐Ÿ’ป Coding Agents - Look up npm/PyPI packages, versions, and READMEs in real time
  • ๐Ÿง  GEO & Brand Visibility - See how ChatGPT, Grok, and Perplexity perceive your brand
  • ๐Ÿ“ Content Creation - Access up-to-date information for writing
  • ๐ŸŽ“ Academic Research - Gather data from multiple sources efficiently

โšก Quick Start

Use the configuration wizard:

GIF for day2

๐Ÿ“ก Use our hosted server - No installation needed!

Perfect for users who want zero setup. Just add this URL to your MCP client:

https://mcp.brightdata.com/mcp?token=YOUR_API_TOKEN_HERE

Setup in Claude Desktop:

  1. Go to: Settings โ†’ Connectors โ†’ Add custom connector
  2. Name: Bright Data Web
  3. URL: https://mcp.brightdata.com/mcp?token=YOUR_API_TOKEN
  4. Click "Add" and you're done! โœจ
Run locally on your machine
{
  "mcpServers": {
    "Bright Data": {
      "command": "npx",
      "args": ["@brightdata/mcp"],
      "env": {
        "API_TOKEN": "<your-api-token-here>"
      }
    }
  }
}

๐Ÿš€ Pricing & Modes

โšก Rapid Mode (Free tier) ๐Ÿ’Ž Pro Mode ๐Ÿ”ง Custom Mode

$0/month

5,000 credits


โœ… Web Search
โœ… Scraping with Web unlocker
โœ… AI-ranked Discover search
โŒ Browser Automation
โŒ Web data tools


Default Mode

Pay-as-you-go

Everything in rapid plus 60+ tools


โœ… Browser Control
โœ… Web Data APIs



PRO_MODE=true

Usage-based

Pick the tools you need


โœ… Combine tool groups
โœ… Add individual tools
โŒ Overrides Pro eligibility


GROUPS="browser"
TOOLS="scrape_as_html"

๐Ÿ’ก How the free tier works: Your account gets 5,000 credits/month
(~$7.50 value), auto-renewed on the 1st with no credit card required.
MCP requests draw from this shared pool - base tools (search_engine,
scrape_as_markdown, discover) cost 1 credit per request, while
web_data_* tools cost 1 credit per record returned. Unused credits
don't roll over, and when they run out requests stop (no surprise
charges unless you've deposited funds). Pro mode is not included in the
free tier and incurs additional charges based on usage.


๐Ÿง  Advanced Tool Selection

  • GROUPS lets you enable curated tool bundles. Use comma-separated group
    IDs such as ecommerce,browser.
  • TOOLS adds explicit tool names on top of the selected groups.
  • Mode priority: PRO_MODE=true (all tools) โ†’ GROUPS / TOOLS
    (whitelist) โ†’ default rapid mode (base toolkit).
  • Base tools always enabled: search_engine, search_engine_batch,
    scrape_as_markdown, scrape_batch, discover.
  • Group ID custom is reserved; use TOOLS for bespoke picks.
Group ID Description Featured tools
ecommerce Retail and marketplace datasets web_data_amazon_product, web_data_walmart_product, web_data_google_shopping
social Social, community, and creator insights web_data_linkedin_posts, web_data_tiktok_posts, web_data_youtube_videos
browser Bright Data Scraping Browser automation tools scraping_browser_snapshot, scraping_browser_click_ref, scraping_browser_screenshot
finance Financial intelligence datasets web_data_yahoo_finance_business
business Company and location intelligence datasets web_data_crunchbase_company, web_data_zoominfo_company_profile, web_data_zillow_properties_listing
research News and developer data feeds web_data_github_repository_file, web_data_reuter_news
app_stores App store data web_data_google_play_store, web_data_apple_app_store
travel Travel information web_data_booking_hotel_listings
geo GEO & LLM brand visibility web_data_chatgpt_ai_insights, web_data_grok_ai_insights, web_data_perplexity_ai_insights
code Package intelligence for coding agents web_data_npm_package, web_data_pypi_package
advanced_scraping Batch and AI-assisted extraction helpers search_engine_batch, scrape_batch, extract

Claude Desktop example

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

Coding agent example (Claude Code / Cursor / Windsurf)

Give your coding agent real-time package intelligence - latest versions, READMEs,
dependencies, and metadata from npm and PyPI without scraping:

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

โœจ Features

๐Ÿ”ฅ Core Capabilities

๐Ÿ” Smart Web Search
Google-quality results optimized for AI
๐Ÿ“„ Clean Markdown
AI-ready content extraction
๐ŸŒ Global Access
Bypass geo-restrictions automatically
๐Ÿ›ก๏ธ Anti-Bot Protection
Never get blocked or rate-limited
๐Ÿค– Browser Automation
Control real browsers remotely (Pro)
โšก Lightning Fast
Optimized for minimal latency

๐ŸŽฏ Example Queries That Just Work

โœ… "What's Tesla's current stock price?"
โœ… "Find the best-rated restaurants in Tokyo right now"
โœ… "Get today's weather forecast for New York"
โœ… "What movies are releasing this week?"
โœ… "What are the trending topics on Twitter today?"
โœ… "What's the latest version of express on npm?"
โœ… "Get the README for the langchain-brightdata PyPI package"

๐ŸŽฌ Demos

Note: These videos show earlier versions. New demos coming soon! ๐ŸŽฅ

View Demo Videos

Basic Web Search Demo

https://github.com/user-attachments/assets/59f6ebba-801a-49ab-8278-1b2120912e33

Advanced Scraping Demo

https://github.com/user-attachments/assets/61ab0bee-fdfa-4d50-b0de-5fab96b4b91d

๐Ÿ“บ More tutorials on YouTube โ†’


๐Ÿ”ง Available Tools

โšก Rapid Mode Tools (Default - Free)

Tool Description Use Case
๐Ÿ” search_engine Web search with AI-optimized results Research, fact-checking, current events
๐Ÿ“„ scrape_as_markdown Convert any webpage to clean markdown Content extraction, documentation
๐ŸŽฏ discover AI-ranked web search with intent-based relevance scoring Deep research, RAG pipelines, competitive analysis

๐Ÿ’Ž Pro Mode Tools (60+ Tools)

Click to see all Pro tools
Category Tools Description
Browser Control scraping_browser.* Full browser automation
Web Data APIs web_data_* Structured data extraction
E-commerce Product scrapers Amazon, eBay, Walmart data
Social Media Social scrapers Twitter, LinkedIn, Instagram
Maps & Local Location tools Google Maps, business data

๐Ÿ“š View complete tool documentation โ†’


๐ŸŽฎ Try It Now!

๐Ÿงช Online Playground

Try the Web MCP without any setup:


๐Ÿ”ง Configuration

Basic Setup

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

Advanced Configuration

{
  "mcpServers": {
    "Bright Data": {
      "command": "npx",
      "args": ["@brightdata/mcp"],
      "env": {
        "API_TOKEN": "your-token-here",
        "PRO_MODE": "true",              // Enable all 60+ tools
        "RATE_LIMIT": "100/1h",          // Custom rate limiting
        "WEB_UNLOCKER_ZONE": "custom",   // Custom unlocker zone
        "BROWSER_ZONE": "custom_browser", // Custom browser zone
        "POLLING_TIMEOUT": "600"         // Polling timeout in seconds (default: 600)
      }
    }
  }
}

Environment Variables

Variable Description Default Example
API_TOKEN Your Bright Data API token (required) - your-token-here
PRO_MODE Enable all 60+ tools false true
RATE_LIMIT Custom rate limiting unlimited 100/1h, 50/30m
WEB_UNLOCKER_ZONE Custom Web Unlocker zone name mcp_unlocker my_custom_zone
BROWSER_ZONE Custom Browser zone name mcp_browser my_browser_zone
POLLING_TIMEOUT Timeout for web_data_* tools polling (seconds) 600 300, 1200
BASE_TIMEOUT Request timeout for base tools in seconds (search & scrape) No limit 60, 120
BASE_MAX_RETRIES Max retries for base tools on transient errors (0-3) 0 1, 3
GROUPS Comma-separated tool group IDs - ecommerce,browser
TOOLS Comma-separated individual tool names - extract,scrape_as_html

Notes:

  • POLLING_TIMEOUT controls how long web_data_* tools wait for results. Each second = 1 polling attempt.
  • Lower values (e.g., 300) will fail faster on slow data collections.
  • Higher values (e.g., 1200) allow more time for complex scraping tasks.

๐Ÿ“š Documentation


๐Ÿšจ Common Issues & Solutions

๐Ÿ”ง Troubleshooting Guide

โŒ "spawn npx ENOENT" Error

Solution: Install Node.js or use the full path to node:

"command": "/usr/local/bin/node"  // macOS/Linux
"command": "C:\\Program Files\\nodejs\\node.exe"  // Windows

โฑ๏ธ Timeouts on Complex Sites

Solution: Increase timeout in your client settings to 180s

๐Ÿ”‘ Authentication Issues

Solution: Ensure your API token is valid and has proper permissions

๐Ÿ“ก Remote Server Connection

Solution: Check your internet connection and firewall settings

More troubleshooting โ†’


๐Ÿค Contributing

We love contributions! Here's how you can help:

Please follow Bright Data's coding standards.


๐Ÿ“ž Support


๐Ÿ“œ License

MIT ยฉ Bright Data Ltd.


Built with โค๏ธ by
Bright Data

The world's #1 web data platform


โญ Star us on GitHub โ€ข Read our Blog

FAQ

Common questions

Discussion

Questions & comments ยท 0

Sign In Sign in to leave a comment.