Brightdata MCP (Luminati Io)

The Web MCP

🌐 Give your AI real-time web superpowers

Seamlessly connect LLMs to the live web without getting blocked

Quick Start • Features • Pricing • Demos • Docs • Support

🎉 Free Tier Available! 🎉

5,000 requests/month FREE

Perfect for prototyping and everyday AI workflows

NEW: Code Tool group - Your Coding Agent's Best Friend

Instant access to npm and PyPI package data, right from your AI agent.

Need the latest version of a package? Want to read its README without leaving your workflow?

The Code tool group gives coding agents structured, reliable package metadata on demand —

no scraping, no stale caches, just the data your agent needs to make smart dependency decisions.

npm Package versions, READMEs, metadata & dependencies PyPI Python package info, versions & project details

GROUPS="code" · The go-to tool for Claude Code, Cursor, Windsurf & any MCP-powered coding agent

GEO & AI Brand Visibility Tools

See how ChatGPT, Grok, and Perplexity talk about your brand.

Query leading LLMs directly from your agent and get back structured, markdown-formatted answers.

The ultimate feedback loop for Generative Engine Optimization (GEO) — monitor AI-generated recommendations, track brand mentions across LLMs, and understand how AI perceives your products.

ChatGPT AI-generated insights, citations & recommendations Grok Real-time AI analysis powered by X data Perplexity Search-augmented AI answers with sources

GROUPS="geo" · Works with any MCP-compatible agent

______________________________________________________________________

🌟 概述

网络MCP 是您为AI助手提供真正网络功能的门户。不再有过时的回复，不再有“我无法访问实时信息”——只是无缝、可靠的网络访问，真正有效。

由...建造 明亮的数据MCP服务器是世界上排名第一的网络数据平台，可确保您的AI永远不会被阻止、限速或提供验证码。

✅ Works with Any LLM Claude, GPT, Gemini, Llama 🛡️ Never Gets Blocked Enterprise-grade unblocking 🚀 5,000 Free Requests Monthly ⚡ Zero Config Works out of the box

______________________________________________________________________

🎯 完美适合

• 🔍 实时研究 -获取当前价格、新闻和实时数据
• 🛍️ 电子商务智能 -监控产品、价格和可用性
• 📊 市场分析 -跟踪竞争对手和行业趋势
• 🤖 AI智能体 -构建可以实际浏览网页的代理
• 💻 编码代理 -实时查找npm/PyPI包、版本和README
• 🧠 地理位置和品牌知名度 -了解ChatGPT、Grok和Perplexity如何看待您的品牌
• 📝 内容创建 -访问最新信息以进行写作
• 🎓 学术研究 -高效地从多个来源收集数据

______________________________________________________________________

⚡ 快速开始

使用配置向导：

📡 Use our hosted server - No installation needed!

非常适合想要零设置的用户。只需将此URL添加到您的MCP客户端：

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

在Claude Desktop中设置：

1. 转到：设置→ 连接器→ 添加自定义连接器
2. 姓名： Bright Data Web
3. 网址： https://mcp.brightdata.com/mcp?token=YOUR_API_TOKEN
4. 点击“添加”，您就完成了！ ✨

Run locally on your machine

{
  "mcpServers": {
    "Bright Data": {
      "command": "npx",
      "args": ["@brightdata/mcp"],
      "env": {
        "API_TOKEN": ""
      }
    }
  }
}

______________________________________________________________________

🚀 定价和模式

⚡ Rapid Mode (Free tier) 💎 Pro Mode 🔧 Custom Mode

$0/month

5,000 requests

✅ Web Search

✅ Scraping with Web unlocker

✅ AI-ranked Discover search

❌ Browser Automation

❌ Web data tools

Default Mode

Pay-as-you-go

Everything in rapid plus 60+ tools

✅ Browser Control

✅ Web Data APIs

PRO_MODE=true

Usage-based

Pick the tools you need

✅ Combine tool groups

✅ Add individual tools

❌ Overrides Pro eligibility

GROUPS="browser"

TOOLS="scrape_as_html"

💡 注： 专业模式是 不包括 在免费等级和招致 根据使用情况收取额外费用。

______________________________________________________________________

🧠 高级工具选择

• GROUPS 允许您启用策划的工具包。使用逗号分隔的组

ID，例如 ecommerce,browser.

• TOOLS 在所选组的顶部添加明确的工具名称。
• 模式优先级： PRO_MODE=true （所有工具）→ GROUPS / TOOLS

（白名单）→ 默认快速模式（基本工具包）。

• 始终启用基本工具： search_engine, search_engine_batch,

scrape_as_markdown, scrape_batch, discover.

• 群组ID custom 保留；使用 TOOLS 定制精选。

Group ID Description Featured tools

ecommerce Retail and marketplace datasets web_data_amazon_product, web_data_walmart_product, web_data_google_shopping

social Social, community, and creator insights web_data_linkedin_posts, web_data_tiktok_posts, web_data_youtube_videos

browser Bright Data Scraping Browser automation tools scraping_browser_snapshot, scraping_browser_click_ref, scraping_browser_screenshot

finance Financial intelligence datasets web_data_yahoo_finance_business

business Company and location intelligence datasets web_data_crunchbase_company, web_data_zoominfo_company_profile, web_data_zillow_properties_listing

research News and developer data feeds web_data_github_repository_file, web_data_reuter_news

app_stores App store data web_data_google_play_store, web_data_apple_app_store

travel Travel information web_data_booking_hotel_listings

geo GEO & LLM brand visibility web_data_chatgpt_ai_insights, web_data_grok_ai_insights, web_data_perplexity_ai_insights

code Package intelligence for coding agents web_data_npm_package, web_data_pypi_package

advanced_scraping Batch and AI-assisted extraction helpers search_engine_batch, scrape_batch, extract

Claude桌面示例

{
  "mcpServers": {
    "Bright Data": {
      "command": "npx",
      "args": ["@brightdata/mcp"],
      "env": {
        "API_TOKEN": "",
        "GROUPS": "browser,advanced_scraping",
        "TOOLS": "extract"
      }
    }
  }
}

编码代理示例（克劳德代码/光标/风帆）

为您的编码代理提供实时包智能——最新版本、README、， 无需抓取npm和PyPI的依赖关系和元数据：

{
  "mcpServers": {
    "Bright Data": {
      "command": "npx",
      "args": ["@brightdata/mcp"],
      "env": {
        "API_TOKEN": "",
        "GROUPS": "code"
      }
    }
  }
}

______________________________________________________________________

✨ 特性

🔥 核心能力

🔍 Smart Web Search Google-quality results optimized for AI 📄 Clean Markdown AI-ready content extraction

🌍 Global Access Bypass geo-restrictions automatically 🛡️ Anti-Bot Protection Never get blocked or rate-limited

🤖 Browser Automation Control real browsers remotely (Pro) ⚡ Lightning Fast Optimized for minimal latency

🎯 简单有效的查询示例

✅ "What's Tesla's current stock price?"
✅ "Find the best-rated restaurants in Tokyo right now"
✅ "Get today's weather forecast for New York"
✅ "What movies are releasing this week?"
✅ "What are the trending topics on Twitter today?"
✅ "What's the latest version of express on npm?"
✅ "Get the README for the langchain-brightdata PyPI package"

______________________________________________________________________

🎬 演示

注： 这些视频显示了早期版本。新演示即将推出！ 🎥

View Demo Videos

基本网络搜索演示

https://github.com/user-attachments/assets/59f6ebba-801a-49ab-8278-1b2120912e33

高级刮擦演示

https://github.com/user-attachments/assets/61ab0bee-fdfa-4d50-b0de-5fab96b4b91d

📺 YouTube上的更多教程→

______________________________________________________________________

🔧 可用工具

⚡ 快速模式工具（默认-免费）

💎 专业模式工具（60+工具）

Click to see all Pro tools

📚 查看完整的工具文档→

______________________________________________________________________

🎮 现在就试试！

🧪 在线游乐场

尝试不进行任何设置的Web MCP：

______________________________________________________________________

🔧 配置

基本设置

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

高级配置

{
  "mcpServers": {
    "Bright Data": {
      "command": "npx",
      "args": ["@brightdata/mcp"],
      "env": {
        "API_TOKEN": "your-token-here",
        "PRO_MODE": "true",              // Enable all 60+ tools
        "RATE_LIMIT": "100/1h",          // Custom rate limiting
        "WEB_UNLOCKER_ZONE": "custom",   // Custom unlocker zone
        "BROWSER_ZONE": "custom_browser", // Custom browser zone
        "POLLING_TIMEOUT": "600"         // Polling timeout in seconds (default: 600)
      }
    }
  }
}

环境变量

笔记：

• POLLING_TIMEOUT 控制web_data\*工具等待结果的时间。每秒=1次轮询尝试。
• 较低的值（例如300）在缓慢的数据收集过程中会更快地失败。
• 更高的值（例如1200）允许更多时间用于复杂的抓取任务。

______________________________________________________________________

📚 文档

______________________________________________________________________

🚨 常见问题及解决方案

🔧 Troubleshooting Guide

❌ “spawn npx ENOENT”错误

解决方案： 安装Node.js或使用节点的完整路径：

"command": "/usr/local/bin/node"  // macOS/Linux
"command": "C:\\Program Files\\nodejs\\node.exe"  // Windows

⏱️ 复杂场地的超时

解决方案： 将客户端设置中的超时时间增加到180秒

🔑 身份验证问题

解决方案： 请确保您的API令牌有效并且具有适当的权限

📡 远程服务器连接

解决方案： 检查您的互联网连接和防火墙设置

更多故障排除→

______________________________________________________________________

🤝 贡献

我们热爱贡献！以下是您可以提供帮助的方式：

• 🐛 报告错误
• 💡 建议功能
• 🔧 提交PR
• ⭐ 星这个回购！

请遵循 Bright Data的编码标准.

______________________________________________________________________

📞 支持

🐛 GitHub Issues

Report bugs & features

📚 Documentation

Complete guides

✉️ Email

support@brightdata.com

______________________________________________________________________

📜 许可证

MIT© 光明数据有限公司。

______________________________________________________________________

Built with ❤️ by

The world's #1 web data platform

⭐ Star us on GitHub • Read our Blog