Brightdata Mcp
brightdata/brightdata-mcp
The Brightdata MCP server connects AI agents to live web data by providing tools for web scraping, real-time data retrieval, and access to package information from npm and PyPI without getting blocked. It offers tool groups including web browsing capabilities, code package metadata access for coding agents, and AI brand visibility tools that query ChatGPT, Grok, and Perplexity to monitor how LLMs discuss brands and products. The server solves the problem of integrating current web information into LLM workflows while handling anti-scraping protections, with a free tier providing 5,000 requests per month.
- GitHub stars
- 2.7K
- tools
- 4
- auth
- Secret needed
- transport
- STDIO
- env vars
- 6
- last updated
- Nov 10, 2026
Tools
4 toolsPublic tool metadata for what this MCP can expose to an agent.
search_engineScrape search results from Google, Bing or Yandex. Returns SERP results in JSON or Markdown (URL, title, description), Ideal for gathering current information, news, and detailed search results.3 params
Scrape search results from Google, Bing or Yandex. Returns SERP results in JSON or Markdown (URL, title, description), Ideal for gathering current information, news, and detailed search results.
Parameters* required
cursorstringPagination cursor for next page
enginestringone of
google · bing · yandexdefault: googlequerystringscrape_as_markdownScrape a single webpage URL with advanced options for content extraction and get back the results in MarkDown language. This tool can unlock any webpage even if it uses bot detection or CAPTCHA.1 params
Scrape a single webpage URL with advanced options for content extraction and get back the results in MarkDown language. This tool can unlock any webpage even if it uses bot detection or CAPTCHA.
Parameters* required
urlstringsearch_engine_batchRun multiple search queries simultaneously. Returns JSON for Google, Markdown for Bing/Yandex.1 params
Run multiple search queries simultaneously. Returns JSON for Google, Markdown for Bing/Yandex.
Parameters* required
queriesarrayscrape_batchScrape multiple webpages URLs with advanced options for content extraction and get back the results in MarkDown language. This tool can unlock any webpage even if it uses bot detection or CAPTCHA.1 params
Scrape multiple webpages URLs with advanced options for content extraction and get back the results in MarkDown language. This tool can unlock any webpage even if it uses bot detection or CAPTCHA.
Parameters* required
urlsarrayArray of URLs to scrape (max 10)
Sponsors
Promote your product hereReach 125k+ visitors monthlyPromote your product hereReach 125k+ visitors monthly
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any language
Agent CaffeineSponsoredClose your lid, come back to finished workSnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthlyWaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthlyknobsSponsoredSee your site on any phone, any day, in any languageConfiguration
API_TOKEN*secretYour API key for Bright Data
BROWSER_ZONEYour browser zone name
GROUPSComma-separated tool group IDs (e.g., 'ecommerce,browser')
TOOLSComma-separated tool names to enable
BASE_TIMEOUTRequest timeout in seconds for base tools (search & scrape). No limit if unset
BASE_MAX_RETRIESMax retries for base tools on transient errors (0-3, default: 0)
Readme
Bright Data MCP
Web search, page scraping, structured data extraction, and browser automation for AI agents and LLMs over the Model Context Protocol.
Works with AI agents, coding agents, chat assistants, and any MCP-compatible client.
Details
- Repository
- github.com/brightdata/brightdata-mcp
- Categories
- Search & Web Crawling, Data & Analytics
- Package
@brightdata/mcp- Transport
- STDIO
- Auth
- Required
- Registry
- MCP registry, active
