Building an AI startup?
What is Bright Data MCP Server?
What is Bright Data MCP Server?
It allows MCP clients like Claude Desktop, Cursor, and Windsurf to search the web, navigate websites, take actions, and retrieve data without getting blocked, making it perfect for web scraping tasks.\
- New MCP users get a free tier with 5,000 requests per month
- Bypassing geo-restrictions to access content regardless of location
- Navigating websites with bot detection protection using unlocker technology
- Structured data extraction from platforms like Amazon, LinkedIn, Instagram, and many other data feeds
- Remote browser automation for complex web interactions
- Access to a global IP network to avoid blocking or rate limiting
- Explore the MCP GitHub repository to review the source code, contribute, or deploy your own instance.
- Read the MCP documentation to understand the API, request structure, and supported features.
- Get your API key
- Try the Bright Data AI Playground to test and experiment with live requests in a no-code environment.
Are there limitations for the Bright Data free tier?
Are there limitations for the Bright Data free tier?
Where do I get my API keys?
Where do I get my API keys?
How do I use Bright Data MCP Server?
How do I use Bright Data MCP Server?
What can I do with Bright Data MCP Server?
What can I do with Bright Data MCP Server?
search_engine: Search Google, Bing, Yandexscrape_as_markdown,scrape_as_html: Get content in clean formatssession_stats: Monitor tool usage
- Amazon:
web_data_amazon_product,web_data_amazon_product_reviews - LinkedIn:
web_data_linkedin_person_profile,web_data_linkedin_company_profile - Instagram:
web_data_instagram_profiles,web_data_instagram_posts,web_data_instagram_reels - Facebook:
web_data_facebook_posts,web_data_facebook_marketplace_listings - Others:
web_data_x_posts,web_data_youtube_videos,web_data_zillow_properties_listing
scraping_browser_navigate,scraping_browser_click,scraping_browser_typescraping_browser_get_html,scraping_browser_screenshot,scraping_browser_wait_for
Which AI agents and tools can integrate with Bright Data MCP Server?
Which AI agents and tools can integrate with Bright Data MCP Server?
- Claude Desktop (Anthropic)
- Cursor IDE
- Windsurf
- LangChain
- AutoGPT / AgentGPT
- Smithery
- Custom LLMs or AI agents that support MCP
- Perform real-time web searches
- Scrape structured data
- Automate browser interactions
- Access geo-restricted or protected content
How do I enable browser control tools?
How do I enable browser control tools?
- Pro mode: Set
&pro=1(remote) orPRO_MODE=true(self-hosted) to enable all tools, including browser automation - Tool groups: Set
&groups=browser(remote) orGROUPS=browser(self-hosted) to enable just the browser automation tools
What tools are available in the Bright Data MCP Server?
What tools are available in the Bright Data MCP Server?
search_engine: Scrape search results from Google, Bing, or Yandexscrape_as_markdown: Scrape a webpage and get results in Markdown formatscrape_as_html: Scrape a webpage and get results in HTML formatsession_stats: View tool usage during the current session
- Amazon:
web_data_amazon_product,web_data_amazon_product_reviews - LinkedIn:
web_data_linkedin_person_profile,web_data_linkedin_company_profile - ZoomInfo:
web_data_zoominfo_company_profile - Instagram:
web_data_instagram_profiles,web_data_instagram_posts,web_data_instagram_reels,web_data_instagram_comments - Facebook:
web_data_facebook_posts,web_data_facebook_marketplace_listings,web_data_facebook_company_reviews - Various others:
web_data_x_posts,web_data_zillow_properties_listing,web_data_booking_hotel_listings,web_data_youtube_videos
scraping_browser_navigate: Navigate to a URLscraping_browser_go_back/scraping_browser_go_forward: Navigate browser historyscraping_browser_click: Click on an elementscraping_browser_links: Get all links on the current pagescraping_browser_type: Type text into an elementscraping_browser_wait_for: Wait for an element to appearscraping_browser_screenshot: Take a screenshotscraping_browser_get_html/scraping_browser_get_text: Get page content
How do I handle timeout issues when using Bright Data MCP Server?
How do I handle timeout issues when using Bright Data MCP Server?
- Set a high enough timeout in your agent settings (180 seconds is recommended)
- For particularly slow sites, you may need to increase this value further
- Use the specialized
web_data_*tools when available, as they’re often faster than general scraping - For browser automation sequences, keep operations close together in time
What security considerations should I keep in mind?
What security considerations should I keep in mind?
- Filter and validate all web data before passing it to the LLM
- Use structured data extraction rather than raw text when possible
- Be cautious with executing JavaScript from scraped content
Why am I getting a 'spawn npx ENOENT' error?
Why am I getting a 'spawn npx ENOENT' error?
npx command. To fix it:- Find your Node.js path:
- On macOS: Run
which nodein Terminal - On Windows: Run
where nodein Command Prompt
- On macOS: Run
- Update your MCP configuration to use the full path instead of
npx:
How do I monitor my usage and costs?
How do I monitor my usage and costs?
session_stats tool to check your usage during the current session. For comprehensive usage tracking and billing information, log in to your Bright Data account dashboard. The session_stats tool will show you information about:- Number of requests made during the current session
- Tools used and their frequency
Is there a playground where I can try Bright Data MCP Server?
Is there a playground where I can try Bright Data MCP Server?
How do I connect my AI agent with Bright Data's MCP?
How do I connect my AI agent with Bright Data's MCP?
- Install Node.js (only required for the self-hosted option)
- Create a Bright Data account (new users get free credit for testing)
- Copy your API key from the user settings page (new users receive an API key in the welcome email)
- Configure your agent with your API key. For more detailed examples, visit us on GitHub or check our MCP documentation.
When using MCP, should I create zones or configure them?
When using MCP, should I create zones or configure them?
Is there a free access tier for the Bright Data MCP?
Is there a free access tier for the Bright Data MCP?
What is the MCP free tier?
What is the MCP free tier?
What happens when the free tier limit is reached?
What happens when the free tier limit is reached?
- Go to brightdata.com/cp and click Add (top-right)
- Select Unlocker zone and create it with any name (e.g.,
my_unlocker) - Update your MCP configuration to use the new zone:
- Remote MCP: Add
&unlocker=ZONE_NAMEto your MCP URL - Self-hosted MCP: Set the
WEB_UNLOCKER_ZONE=ZONE_NAMEenvironment variable
- Remote MCP: Add
- Restart your MCP client (e.g., Claude Desktop, Cursor) after the configuration change
Can I run multiple MCP instances in parallel?
Can I run multiple MCP instances in parallel?
npx, each instance downloads and caches the package separately, which can consume significant disk space.For parallel use cases, we recommend using the Remote MCP instead. It requires no local installation, runs entirely in the cloud, and eliminates disk space concerns. Simply point each instance to the remote endpoint: