MCP App Store
by KeenEthics
Bright Data icon

Bright Data MCP Server for Claude and ChatGPT

By Bright Data

Overview

Bright Data brings live public web data into Claude. Search the web: get live Google or Bing results for one query, or up to 5 queries at once. Read pages: open public pages live, at the moment you ask, so answers use the page as it is right now. Get each page as clean markdown, plain text, HTML, or schema.org data when the page has it, one page or up to 5 at a time. Sign in with your Bright Data account to start. There is no API key to copy. Requests run on your account, and new accounts include 5,000 free requests a month with no credit card.

How to connect

  1. Claude: Open the Bright Data listing in the Claude connectors directory and choose Connect. Claude listing Bright Data exposes 4 tools here.
  2. ChatGPT: Open the Bright Data listing in the ChatGPT app directory and choose Connect. ChatGPT listing Bright Data exposes 4 tools here.

Tools

scrape_as_markdown

ChatGPT
Fetch one web page. Returns JSON: url, format, content, plus title and note when present. content is the page in one format, markdown by default. Pick another with the format param: - text: plain text, no links or headings - html: raw HTML, for CSS selectors or data hidden in the markup - ld_json: schema.org data (price, rating, author...) If the page has no data in that format, markdown is returned instead, with a note. No JavaScript rendering. Pages that take longer than 45 s time out. Pages over 40,000 characters are cut. To read the rest for free, call again with the snapshot_id and start values from the result's next field.

scrape_batch

ChatGPT
Fetch up to 5 web pages at once. Returns a JSON array in input order, one item per URL: url, format, content, plus title and note when present; or url and error if that page failed. content is the page in one format, markdown by default. Pick another with the format param: - text: plain text, no links or headings - html: raw HTML, for CSS selectors or data hidden in the markup - ld_json: schema.org data (price, rating, author...) If a page has no data in that format, markdown is returned instead, with a note. No JavaScript rendering. Pages that take longer than 35 s time out (45 s when only one URL is sent). The whole result is cut at 40,000 characters, shared between pages. To read the rest of a cut page for free, call scrape_as_markdown with its url and the snapshot_id and start values from that item's next field.

search_engine

ChatGPT
Search Bing (default) or Google. Returns JSON: organic results with link, title and description. Searches not done within 55 s return a timeout error.

search_engine_batch

ChatGPT
Run up to 5 searches at once, on Bing (default) or Google. Returns a JSON array in input order: query, engine, and result (organic link, title, description) or error. Searches not done within 55 s return a timeout error.

scrape_as_markdown

Claude

scrape_batch

Claude

search_engine

Claude

search_engine_batch

Claude

Similar Apps

Listed on MCP App Store

Listed on MCP App Store

Add this badge to your site or README. It links to this page.

HTML

<a href="https://mcp-app-store.keenethics-labs.com/app/bright-data"><img src="https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg" alt="Listed on MCP App Store" width="220" height="44"></a>

Markdown

[![Listed on MCP App Store](https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg)](https://mcp-app-store.keenethics-labs.com/app/bright-data)