MCP.so
登录
服务器

Bright Data MCP

@brightdata-com

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

概览

What is Bright Data MCP?

Bright Data MCP is an MCP server that gives AI assistants real-time web access through Bright Data's web data platform. It enables LLMs to search, scrape, and interact with live websites without getting blocked, rate-limited, or served CAPTCHAs, and offers a free tier of 5,000 credits per month.

How to use Bright Data MCP?

Use Bright Data MCP via a hosted server (no installation) by adding https://mcp.brightdata.com/mcp?token=YOUR_API_TOKEN to your MCP client, or run locally using npx @brightdata/mcp with the API_TOKEN environment variable. Optionally configure tool groups with the GROUPS env variable (e.g., GROUPS="browser,code") or enable Pro mode with PRO_MODE=true.

Key features of Bright Data MCP

  • Smart web search optimized for AI consumption
  • Clean markdown extraction from any webpage
  • Enterprise-grade anti-bot and geo-unblocking protection
  • Browser automation (Pro mode) for complex interactions
  • Curated tool groups for ecommerce, social, finance, code, and more
  • Base tools always enabled: search, scrape, and discover

Use cases of Bright Data MCP

  • Real-time market research and price monitoring
  • E-commerce product and availability tracking
  • Competitive intelligence and trend analysis
  • AI coding agents retrieving npm/PyPI package data
  • GEO and brand visibility monitoring across ChatGPT, Grok, and Perplexity

FAQ from Bright Data MCP

What is the free tier and how many credits do I get?

The free "Rapid" mode gives you 5,000 credits per month, auto-renewed on the 1st with no credit card required. Base tools (search, scrape, discover) cost 1 credit per request; web data tools cost 1 credit per record. Unused credits don't roll over, and when they run out requests stop without surprise charges.

How do I configure which tools are available?

Set the GROUPS environment variable to a comma-separated list of group IDs (e.g., ecommerce,browser,code) to enable curated tool bundles. Use TOOLS to add individual tools on top. Set PRO_MODE=true for all 60+ tools. Base tools are always enabled regardless.

What are the base tools always enabled?

The always-enabled base tools are: search_engine, search_engine_batch, scrape_as_markdown, scrape_batch, and discover. These provide core web search and scraping functionality.

How do I get started quickly with Bright Data MCP?

For hosted use, add the URL https://mcp.brightdata.com/mcp?token=YOUR_API_TOKEN to your MCP client (e.g., Claude Desktop). For local use, run npx @brightdata/mcp with the API_TOKEN environment variable set. No further configuration needed for the free tier.

Is a credit card required to start using Bright Data MCP?

No. The free tier of 5,000 credits per month requires no credit card. You only need an API token from Bright Data to begin.

标签

来自「数据与分析」的更多内容