MCP Catalogs
Homebrightdata-mcp screenshot

brightdata-mcp

by brightdata·2,366·Score 57

A powerful MCP server providing real-time web access without blocking for AI agents.

web-scrapingdeveloper-toolsai-llm
303
Forks
14
Open issues
1 mo ago
Last commit
2d ago
Indexed

Overview

The Web MCP by Bright Data is an all-in-one solution that gives AI assistants real-time web superpowers. Built by the world's #1 web data platform, this server ensures AI agents never get blocked, rate-limited, or encounter CAPTCHAs when accessing online information. It offers multiple pricing tiers including a generous free plan with 5,000 requests per month, making it accessible for both prototyping and production use.

Try asking AI

After installing, here are 5 things you can ask your AI assistant:

you:Real-time research for current prices, news, and live data
you:E-commerce intelligence and price monitoring
you:Coding agents accessing npm/PyPI package metadata and READMEs
you:Is there a free tier available?
you:What LLMs does this MCP server work with?

When to choose this

Choose this MCP server when your AI agents need reliable, real-time web access without getting blocked, especially for research, data collection, or specialized knowledge extraction.

When NOT to choose this

Don't choose this if you need open-source self-hosting without vendor lock-in, as it requires an API token from BrightData and has limited free tier.

Tools this server exposes

12 tools extracted from the README
  • search_engine

    Web search with AI-optimized results

  • scrape_as_markdown

    Convert any webpage to clean markdown

  • discover

    AI-ranked web search with intent-based relevance scoring

  • web_data_npm_package

    Get npm package versions, READMEs, metadata & dependencies

  • web_data_pypi_package

    Get Python package info, versions & project details from PyPI

  • web_data_chatgpt_ai_insights

    Get AI-generated insights, citations & recommendations from ChatGPT

  • web_data_grok_ai_insights

    Get real-time AI analysis powered by X data from Grok

  • web_data_perplexity_ai_insights

    Get search-augmented AI answers with sources from Perplexity

  • scraping_browser_snapshot

    Take a snapshot of a webpage using a real browser

  • scrape_batch

    Scrape multiple webpages in a single request

  • extract

    AI-assisted extraction of specific data from webpages

  • search_engine_batch

    Perform multiple web searches in a single request

Comparable tools

browserless-mcpscrapingbee-mcpweb-scraper-apiapify-mcprequests-html

Installation

Quick Start

**Use the hosted server (recommended):** Add this URL to your MCP client configuration:

https://mcp.brightdata.com/mcp?token=YOUR_API_TOKEN_HERE

**Run locally:**

{
  "mcpServers": {
    "Bright Data": {
      "command": "npx",
      "args": ["@brightdata/mcp"],
      "env": {
        "API_TOKEN": "<your-api-token-here>"
      }
    }
  }
}

**Claude Desktop setup:**

  1. Go to Settings → Connectors → Add custom connector
  2. Name: Bright Data Web
  3. URL: https://mcp.brightdata.com/mcp?token=YOUR_API_TOKEN
  4. Click "Add"

FAQ

Is there a free tier available?
Yes, there's a free tier with 5,000 requests per month, perfect for prototyping and everyday AI workflows.
What LLMs does this MCP server work with?
It works with any LLM including Claude, GPT, Gemini, Llama, and other MCP-compatible agents.

On Hacker News

Recent discussion from the developer community.

Compare brightdata-mcp with

GitHub →

Last updated · Auto-generated from public README + GitHub signals.