# brightdata/brightdata-mcp

A powerful Model Context Protocol (MCP) server that provides an all-in-one solution for public web access.

Repository: https://github.com/brightdata/brightdata-mcp
Canonical: https://ross.abutalabs.com/products/brightdata-mcp
Homepage: https://brightdata.com/
Language: JavaScript
License: MIT
License Family: permissive
Topics: llm, mcp, modelcontextprotocol, scraping, ai-agents, ai-integrations, anti-bot-detection, browser-automation, data-collection, data-extraction, mcp-server, scraping-tools, structured-data, web-crawling, web-data, web-scraping
Last push: 2026-08-12T07:39:54+00:00

## Health v2 (maintenance only)
Score: 84/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 97, release rhythm 95, longevity 36
- inputs: {"age_days": 505, "days_push": 21, "days_rel": 37, "gap_med": 19, "n_releases_24m": 12}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2610, forks 324 (observed 2026-08-28T04:07:04.299231+00:00)

## What it is
A Model Context Protocol (MCP) server by Bright Data that gives AI agents and LLMs real-time access to public web data through 69 tools covering web search, page scraping, structured data extraction, and remote browser automation. Requests are routed through Bright Data's unblocking infrastructure (proxy rotation, CAPTCHA solving, bot detection bypass), deployable as a hosted remote server or locally via npx.

## Use cases
- give my AI agent real-time web search and scraping tools
- scrape any URL as markdown for an LLM without getting blocked
- extract structured JSON from Amazon, LinkedIn, or Instagram profiles
- add browser automation to an MCP-compatible coding agent
- bypass CAPTCHAs and bot detection when collecting web data
- feed live web data into a RAG pipeline
- collect LLM responses from ChatGPT or Perplexity programmatically

## When to choose
- you need an MCP server that handles anti-bot measures, CAPTCHAs, and proxies automatically
- you want structured data from major platforms without writing parsers
- you want a hosted web-access layer for AI agents with a free monthly tier
- you need both search results and full browser automation in one tool set

## When to avoid
- you need a fully free, self-contained scraper with no external service dependency
- your use case exceeds the free tier and you cannot accept per-request pricing
- you only need simple scraping of non-protected sites where a lightweight open-source scraper suffices
- you require on-premises data handling with no third-party routing

## Facets
- artifact type: service
- maturity: active
- function: web-scraping, search-engine, mcp, agent-framework, data-science
- domain: crawlers, artificial-intelligence, large-language-models, developer-tools
- platform: cloud, self-hosted, cross-platform
- tags: model-context-protocol, mcp-server, anti-bot-bypass, captcha-solving, proxy-rotation, structured-data-extraction, serp-api, browser-automation, llm-tools, web-data, hosted-and-local, freemium, ai-agents, data-engineering, nodejs

## Member repositories
- brightdata/brightdata-mcp (main) score 84

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:04.299231+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:20:52.782591+00:00, confidence not recorded.
  - readme: https://github.com/brightdata/brightdata-mcp (fetched 2026-08-28T04:07:04.299231+00:00, sha e39e75d96530)
  - homepage: https://brightdata.com/ (fetched 2026-08-29T10:04:01.428146+00:00, sha f36ad7f437db)
  - site_page: https://docs.brightdata.com/integrations/ai-integrations (fetched 2026-08-29T10:04:01.437179+00:00, sha 390a4a93ef89)
  - site_page: https://brightdata.com/pricing/web-unlocker (fetched 2026-08-29T10:04:01.439314+00:00, sha b4a16ac68664)
  - site_page: https://brightdata.com/pricing/crawl-api (fetched 2026-08-29T10:04:01.441187+00:00, sha a910a9f962dc)
  - site_page: https://brightdata.com/pricing/serp (fetched 2026-08-29T10:04:01.442953+00:00, sha 43f2c580cb7f)
  - site_page: https://brightdata.com/pricing/scraping-browser (fetched 2026-08-29T10:04:01.444771+00:00, sha e829223bf2f0)
  - site_page: https://brightdata.com/pricing/web-scraper (fetched 2026-08-29T10:04:01.446653+00:00, sha 31bb021b1057)
  - site_page: https://brightdata.com/pricing/web-scraper/studio (fetched 2026-08-29T10:04:01.459160+00:00, sha 8290b7c4e105)
  - site_page: https://brightdata.com/pricing/datasets (fetched 2026-08-29T10:04:01.532760+00:00, sha 9c4ed4073b7f)
- Data as of 2026-08-30T08:39:29.467469+00:00.