Best for
- AI agents that need live public web data
- Research and analytics workflows requiring scraping or structured data
- Coding agents that need current npm or PyPI package information
- Users requiring browser automation through Pro mode
B
Bright Data Web MCP
Official
Real-time, unblocked public web access for AI
GitHub source repository ↗
58FMRS · C
Bright Data Web MCP is an MIT-licensed, stdio-based public web access server offering search, scraping, browser automation, and structured data tools. It suits real-time web research and AI-agent workflows, but requires a Bright Data API_TOKEN and involves credit consumption and possible Pro usage charges.
Bright Data's Web MCP server enables AI agents to search, scrape, extract, and navigate the live public web. It provides Markdown extraction, AI-ranked discovery search, browser automation, and data tools for e-commerce, social, finance, business, research, app stores, travel, GEO, and package intelligence.
Tools
search_engine
Runs AI-optimized web search.
search_engine_batch
Runs web searches in batches.
scrape_as_markdown
Converts webpages into AI-ready Markdown.
scrape_batch
Scrapes webpages in batches.
discover
Runs AI-ranked web search with intent-based relevance scoring.
scraping_browser_snapshot
Gets a browser page snapshot.
scraping_browser_click_ref
Clicks a referenced browser element.
scraping_browser_screenshot
Gets a browser page screenshot.
web_data_amazon_product
Extracts structured Amazon product data.
web_data_walmart_product
Extracts structured Walmart product data.
web_data_google_shopping
Extracts Google Shopping data.
web_data_linkedin_posts
Extracts LinkedIn post data.
web_data_tiktok_posts
Extracts TikTok post data.
web_data_youtube_videos
Extracts YouTube video data.
web_data_yahoo_finance_business
Extracts Yahoo Finance business data.
web_data_crunchbase_company
Extracts Crunchbase company data.
web_data_zoominfo_company_profile
Extracts ZoomInfo company profile data.
web_data_zillow_properties_listing
Extracts Zillow property listing data.
web_data_github_repository_file
Extracts GitHub repository file data.
web_data_reuter_news
Extracts Reuters news data.
web_data_google_play_store
Extracts Google Play Store data.
web_data_apple_app_store
Extracts Apple App Store data.
web_data_booking_hotel_listings
Extracts Booking hotel listing data.
web_data_chatgpt_ai_insights
Returns ChatGPT-generated brand insights, citations, and recommendations.
web_data_grok_ai_insights
Returns AI insights from Grok.
web_data_perplexity_ai_insights
Returns search-augmented Perplexity answers with sources.
web_data_npm_package
Returns npm package versions, READMEs, metadata, and dependencies.
web_data_pypi_package
Returns PyPI package information, versions, and project details.
extract
Provides AI-assisted data extraction helpers.
Setup
Configure the server over stdio in an MCP client, run npx @brightdata/mcp, and set API_TOKEN to a Bright Data API key. The README also provides a hosted URL, but that remote option does not change the manifest transport recorded here.
claude_desktop_config.json
{"mcpServers":{"Bright Data":{"command":"npx","args":["@brightdata/mcp"],"env":{"API_TOKEN":"<your-api-token-here>"}}}}
Fit and risk
Not for
- Private, unauthorized, or internal data access
- Users unwilling to provide a Bright Data API key
- Offline environments or local setups without Node.js/npx
- Workflows that cannot accommodate usage-based Pro or web-data costs
Required permissions
- A Bright Data API_TOKEN is required
- The server needs access to Bright Data services and the public web
- WEB_UNLOCKER_ZONE and BROWSER_ZONE may be configured optionally
- PRO_MODE, GROUPS, TOOLS, timeout, and retry settings may be configured optionally
Risks and side effects
- Requests consume account credits; base tools are charged per request and web_data_* tools per returned record
- The free tier provides 5,000 credits per month and unused credits do not roll over
- PRO_MODE incurs additional usage-based charges
- API_TOKEN is a secret credential and should not be exposed in logs or shared configuration
- Live web content, availability, and scraping results may depend on target sites and network conditions
Troubleshooting
- For spawn npx ENOENT, check that Node.js is installed or configure the full node path
- For complex-site timeouts, check and increase the client timeout
- For authentication failures, verify the API_TOKEN and its permissions
- For remote connection failures, check network connectivity and firewall settings
- For slow data-tool responses, check the POLLING_TIMEOUT setting
Use cases
Real-time research and fact-checking
E-commerce price, product, and availability analysis
Competitive and market analysis
Web-enabled AI agents
Real-time npm and PyPI package lookup
GEO and brand visibility analysis
Content creation and academic research
Supported clients
Claude DesktopFull support
Claude CodePartial support
CursorPartial support
WindsurfPartial support