brightdata/brightdata-mcp

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

What it solves

Bright Data MCP provides AI agents and LLMs with reliable, real-time access to public web data. It solves the problem of agents being blocked by bot detection, CAPTCHAs, and geo-restrictions when attempting to scrape or search the web. It also eliminates the need for developers to maintain their own headless browsers, proxy rotations, or complex HTML parsing logic.

How it works

The project is a server implementing the Model Context Protocol (MCP), which allows it to be plugged into compatible AI clients (like Claude Desktop, Cursor, or Windsurf). It exposes 69 different tools that route requests through Bright Data's unblocking infrastructure. These tools can be deployed as a hosted remote server via a single URL or as a local instance using npx.

Who it’s for

  • AI Agent Developers: Those building agents that need to perform real-time research, market analysis, or e-commerce intelligence.
  • Coding Agents: Developers using AI coding assistants that need up-to-date package registry data from npm and PyPI.
  • Market Researchers: Users who need structured JSON data from major platforms like Amazon, LinkedIn, and TikTok without writing custom scrapers.

Highlights

  • Extensive Toolset: 69 tools covering web search (Google, Bing, Yandex), page scraping, and structured data extraction from 45+ platforms.
  • Unblocking Infrastructure: Built-in bypass for bot detection, CAPTCHAs, and proxy rotation on every request.
  • Structured Data: Provides clean JSON for major e-commerce and social media sites instead of raw HTML.
  • Browser Automation: Includes 13 tools for interacting with remote browser sessions (clicking, typing, screenshots).
  • LLM Insights: Tools to collect responses from ChatGPT, Grok, and Perplexity to analyze brand visibility.
  • Batch Operations: Ability to perform up to 10 searches or scrapes in a single call.
  • Easy Deployment: Supports both a hosted remote server and local npx installation.

Related

  • Project
    anysearch-ai/anysearch-mcp-server

    AnySearch MCP Server is a real‑time, MCP‑compatible backend that provides general web search, vertical‑domain search, parallel batch search, and URL‑content extraction. It works with popular AI‑assistant IDEs (OpenCode, Claude Code, Cursor, VS Code, Windsurf, Cline) via simple JSON configuration, supports optional API‑key authentication for higher rate limits, and even allows anonymous use. The README details registration, key handling, client‑specific config snippets, and the four tool endpoints (`search`, `get_sub_domains`, `batch_search`, `extract`).

  • Project
    atilaahmettaner/tradingview-mcp

    An MCP server that provides AI assistants with real-time market data, technical analysis tools, and backtesting capabilities for stocks, crypto, and forex.

  • Project
    vibheksoni/stealth-browser-mcp

    An MCP-compatible server for stealthy browser automation that allows AI agents to bypass anti-bot checks and Cloudflare challenges using real Chrome instances.

  • Project
    dbt-labs/dbt-mcp

    An MCP server that gives AI agents the tools to interact with dbt projects, allowing them to execute SQL, analyze data lineage, and manage dbt pipelines.

  • Project
    dondai1234/master-fetch

    An MCP server that gives AI agents free, keyless web search and anti-bot fetching capabilities, allowing them to bypass bot walls and crawl the web locally.