io.github.brightdata/brightdata-mcp MCP Server
io.github.brightdata/brightdata-mcp
Give AI agents real-time web superpowers—search, scrape, and navigate the live web without getting blocked.
What this kind of tool is for
- Let your agent search the web or a document set and cite what it found.
- Pull structured facts out of pages instead of copy-pasting by hand.
- Track changes on a topic over days without re-reading everything.
How to compare servers like this
- Source coverage:
- Check which engines, sites, or document types the tool can actually reach.
- Citation behavior:
- Prefer tools that return links you can open, not just summarized claims.
- Terms of service:
- Some sources forbid automated access; make sure the tool stays inside them.
- Maintenance signal:
- Scrapers break silently when pages change; recent commits are the best proxy.
This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.
What is the io.github.brightdata/brightdata-mcp MCP server?
The Web MCP is Bright Data's Model Context Protocol server that enables AI assistants to access real-time web data, perform searches, scrape content, and automate browser tasks. It provides enterprise-grade unblocking and structured data extraction from 60+ web sources, with a free tier of 5,000 credits/month.
The Web MCP connects AI agents like Claude and Cursor to the live web with anti-bot protection, geo-bypass, and clean markdown extraction. It offers three pricing tiers: a free Rapid Mode with web search and scraping, a Pro Mode with browser automation and 60+ specialized tools, and a Custom Mode for picking specific tool groups. Perfect for real-time research, e-commerce intelligence, market analysis, coding agents, and brand monitoring across AI platforms.
How to install io.github.brightdata/brightdata-mcp
Copy-paste configuration for popular MCP clients.
API_TOKENrequiredsecretYour API key for Bright Data
WEB_UNLOCKER_ZONEYour unlocker zone name
BROWSER_ZONEYour browser zone name
PRO_MODETo enable PRO_MODE - set to true
GROUPSComma-separated tool group IDs (e.g., 'ecommerce,browser')
TOOLSComma-separated tool names to enable
POLLING_TIMEOUTPolling timeout in seconds for web_data_* tools (default: 600)
BASE_TIMEOUTRequest timeout in seconds for base tools (search & scrape). No limit if unset
BASE_MAX_RETRIESMax retries for base tools on transient errors (0-3, default: 0)
{
"mcpServers": {
"brightdata-mcp": {
"command": "npx",
"args": [
"-y",
"@brightdata/mcp"
],
"env": {
"API_TOKEN": "<YOUR_API_TOKEN>",
"WEB_UNLOCKER_ZONE": "<YOUR_WEB_UNLOCKER_ZONE>",
"BROWSER_ZONE": "<YOUR_BROWSER_ZONE>",
"PRO_MODE": "<YOUR_PRO_MODE>",
"GROUPS": "<YOUR_GROUPS>",
"TOOLS": "<YOUR_TOOLS>",
"POLLING_TIMEOUT": "<YOUR_POLLING_TIMEOUT>",
"BASE_TIMEOUT": "<YOUR_BASE_TIMEOUT>",
"BASE_MAX_RETRIES": "<YOUR_BASE_MAX_RETRIES>"
}
}
}
}Tools & capabilities
Tools this server exposes to the agent.
search_engine— Web search with AI-optimized results for research and fact-checkingscrape_as_markdown— Convert webpages to clean markdown for content extractiondiscover— AI-ranked web search with intent-based relevance scoring for deep researchsearch_engine_batch— Batch web search requestsscrape_batch— Batch scraping requestsscraping_browser_snapshot— Browser automation—capture page snapshotsscraping_browser_click_ref— Browser automation—click elements and interact with pagesscraping_browser_screenshot— Browser automation—take screenshots of rendered pagesweb_data_amazon_product— Extract structured Amazon product dataweb_data_walmart_product— Extract structured Walmart product dataweb_data_google_shopping— Extract Google Shopping product listingsweb_data_linkedin_posts— Extract LinkedIn post dataweb_data_tiktok_posts— Extract TikTok post dataweb_data_youtube_videos— Extract YouTube video dataweb_data_yahoo_finance_business— Extract financial intelligence dataweb_data_crunchbase_company— Extract company intelligence from Crunchbaseweb_data_zoominfo_company_profile— Extract company profiles from ZoomInfoweb_data_zillow_properties_listing— Extract property listings from Zillowweb_data_github_repository_file— Extract GitHub repository file dataweb_data_reuter_news— Extract Reuters news articles
Use cases
- Monitor real-time product prices and availability across e-commerce platforms for competitive analysis
- Track how ChatGPT, Grok, and Perplexity mention your brand to optimize for Generative Engine Optimization (GEO)
- Look up npm and PyPI package versions, READMEs, and dependencies in real time for coding agents
- Gather current news, market trends, and competitor intelligence without outdated training data
- Automate browser interactions to test web applications, fill forms, and capture dynamic content
io.github.brightdata/brightdata-mcp MCP server FAQ
The Web MCP is Bright Data's MCP server that gives AI agents real-time web access with search, scraping, browser automation, and structured data extraction from 60+ sources. It includes anti-bot protection and geo-bypass to prevent blocking.
Yes. The free Rapid Mode includes 5,000 credits/month (no credit card required, auto-renews monthly) covering web search, markdown scraping, and AI-ranked discovery. Pro Mode and specialized tools incur additional usage-based charges.
Add the MCP server to your client config with your API token. For Claude Desktop: Settings → Connectors → Add custom connector, then use the hosted URL or local npm installation. For Cursor/Windsurf: configure in your MCP settings JSON with the @brightdata/mcp npm package.
Yes, you need a Bright Data API token. Sign up at brightdata.com to get your free token and 5,000 monthly credits.
The free Rapid Mode includes search_engine, scrape_as_markdown, discover, search_engine_batch, and scrape_batch. Pro Mode (paid) adds 60+ specialized tools for e-commerce, social media, browser automation, and more.
Yes, the Web MCP works with any MCP-compatible AI: Claude, GPT, Gemini, Llama, and others. It can be deployed as a hosted server or run locally.
README (reference)
Source of truth, from the repository.
🌟 Overview
The Web MCP is your gateway to giving AI assistants true web capabilities. No more outdated responses, no more "I can't access real-time information" - just seamless, reliable web access that actually works.
Built by Bright Data, the world's #1 web data platform, this MCP server ensures your AI never gets blocked, rate-limited, or served CAPTCHAs.
<div align="center"> <table> <tr> <td align="center">✅ <strong>Works with Any LLM</strong><br/><sub>Claude, GPT, Gemini, Llama</sub></td> <td align="center">🛡️ <strong>Never Gets Blocked</strong><br/><sub>Enterprise-grade unblocking</sub></td> <td align="center">🚀 <strong>5,000 Free Credits</strong><br/><sub>Monthly · No card needed</sub></td> <td align="center">⚡ <strong>Zero Config</strong><br/><sub>Works out of the box</sub></td> </tr> </table> </div>🎯 Perfect For
- 🔍 Real-time Research - Get current prices, news, and live data
- 🛍️ E-commerce Intelligence - Monitor products, prices, and availability
- 📊 Market Analysis - Track competitors and industry trends
- 🤖 AI Agents - Build agents that can actually browse the web
- 💻 Coding Agents - Look up npm/PyPI packages, versions, and READMEs in real time
- 🧠 GEO & Brand Visibility - See how ChatGPT, Grok, and Perplexity perceive your brand
- 📝 Content Creation - Access up-to-date information for writing
- 🎓 Academic Research - Gather data from multiple sources efficiently
⚡ Quick Start
Use the configuration wizard:
Perfect for users who want zero setup. Just add this URL to your MCP client:
https://mcp.brightdata.com/mcp?token=YOUR_API_TOKEN_HERE
Setup in Claude Desktop:
- Go to: Settings → Connectors → Add custom connector
- Name:
Bright Data Web - URL:
https://mcp.brightdata.com/mcp?token=YOUR_API_TOKEN - Click "Add" and you're done! ✨
{
"mcpServers": {
"Bright Data": {
"command": "npx",
"args": ["@brightdata/mcp"],
"env": {
"API_TOKEN": "<your-api-token-here>"
}
}
}
}
🚀 Pricing & Modes
<div align="center"> <table> <tr> <th width="33%">⚡ Rapid Mode (Free tier)</th> <th width="33%">💎 Pro Mode</th> <th width="34%">🔧 Custom Mode</th> </tr> <tr> <td align="center"> <h3>$0/month</h3> <p><strong>5,000 credits</strong></p> <hr/> <p>✅ Web Search<br/> ✅ Scraping with Web unlocker<br/> ✅ AI-ranked Discover search<br/> ❌ Browser Automation<br/> ❌ Web data tools</p> <br/> <code>Default Mode</code> </td> <td align="center"> <h3>Pay-as-you-go</h3> <p><strong>Everything in rapid plus 60+ tools</strong></p> <hr/> <p>✅ Browser Control<br/> ✅ Web Data APIs<br/> <br/> <br/> <br/> <code>PRO_MODE=true</code> </td> <td align="center"> <h3>Usage-based</h3> <p><strong>Pick the tools you need</strong></p> <hr/> <p>✅ Combine tool groups<br/> ✅ Add individual tools<br/> ❌ Overrides Pro eligibility</p> <br/> <code>GROUPS="browser"</code><br/> <code>TOOLS="scrape_as_html"</code> </td> </tr> </table> </div>💡 How the free tier works: Your account gets 5,000 credits/month (~$7.50 value), auto-renewed on the 1st with no credit card required. MCP requests draw from this shared pool — base tools (
search_engine,scrape_as_markdown,discover) cost 1 credit per request, whileweb_data_*tools cost 1 credit per record returned. Unused credits don't roll over, and when they run out requests stop (no surprise charges unless you've deposited funds). Pro mode is not included in the free tier and incurs additional charges based on usage.
🧠 Advanced Tool Selection
GROUPSlets you enable curated tool bundles. Use comma-separated group IDs such asecommerce,browser.TOOLSadds explicit tool names on top of the selected groups.- Mode priority:
PRO_MODE=true(all tools) →GROUPS/TOOLS(whitelist) → default rapid mode (base toolkit). - Base tools always enabled:
search_engine,search_engine_batch,scrape_as_markdown,scrape_batch,discover. - Group ID
customis reserved; useTOOLSfor bespoke picks.
Claude Desktop example
{
"mcpServers": {
"Bright Data": {
"command": "npx",
"args": ["@brightdata/mcp"],
"env": {
"API_TOKEN": "<your-api-token-here>",
"GROUPS": "browser,advanced_scraping",
"TOOLS": "extract"
}
}
}
}
Coding agent example (Claude Code / Cursor / Windsurf)
Give your coding agent real-time package intelligence — latest versions, READMEs, dependencies, and metadata from npm and PyPI without scraping:
{
"mcpServers": {
"Bright Data": {
"command": "npx",
"args": ["@brightdata/mcp"],
"env": {
"API_TOKEN": "<your-api-token-here>",
"GROUPS": "code"
}
}
}
}
✨ Features
🔥 Core Capabilities
<table> <tr> <td>🔍 <b>Smart Web Search</b><br/>Google-quality results optimized for AI</td> <td>📄 <b>Clean Markdown</b><br/>AI-ready content extraction</td> </tr> <tr> <td>🌍 <b>Global Access</b><br/>Bypass geo-restrictions automatically</td> <td>🛡️ <b>Anti-Bot Protection</b><br/>Never get blocked or rate-limited</td> </tr> <tr> <td>🤖 <b>Browser Automation</b><br/>Control real browsers remotely (Pro)</td> <td>⚡ <b>Lightning Fast</b><br/>Optimized for minimal latency</td> </tr> </table>🎯 Example Queries That Just Work
✅ "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"
🎬 Demos
<details> <summary><b>View Demo Videos</b></summary>Note: These videos show earlier versions. New demos coming soon! 🎥
Basic Web Search Demo
https://github.com/user-attachments/assets/59f6ebba-801a-49ab-8278-1b2120912e33
Advanced Scraping Demo
https://github.com/user-attachments/assets/61ab0bee-fdfa-4d50-b0de-5fab96b4b91d
</details>🔧 Available Tools
⚡ Rapid Mode Tools (Default - Free)
| Tool | Description | Use Case |
|---|---|---|
🔍 search_engine | Web search with AI-optimized results | Research, fact-checking, current events |
📄 scrape_as_markdown | Convert any webpage to clean markdown | Content extraction, documentation |
🎯 discover | AI-ranked web search with intent-based relevance scoring | Deep research, RAG pipelines, competitive analysis |
💎 Pro Mode Tools (60+ Tools)
<details> <summary><b>Click to see all Pro tools</b></summary>| Category | Tools | Description |
|---|---|---|
| Browser Control | scraping_browser.* | Full browser automation |
| Web Data APIs | web_data_* | Structured data extraction |
| E-commerce | Product scrapers | Amazon, eBay, Walmart data |
| Social Media | Social scrapers | Twitter, LinkedIn, Instagram |
| Maps & Local | Location tools | Google Maps, business data |
📚 View complete tool documentation →
</details>🎮 Try It Now!
🧪 Online Playground
Try the Web MCP without any setup:
<div align="center"> <a href="https://brightdata.com/ai/playground-chat"> <img src="https://img.shields.io/badge/Try_on-Playground-00C7B7?style=for-the-badge&logo=data:image/svg+xml;base64,PHN2ZyB3aWR0aD0iMjQiIGhlaWdodD0iMjQiIHZpZXdCb3g9IjAgMCAyNCAyNCIgZmlsbD0ibm9uZSIgeG1sbnM9Imh0dHA6Ly93d3cudzMub3JnLzIwMDAvc3ZnIj4KPHBhdGggZD0iTTEyIDJMMyA3VjE3TDEyIDIyTDIxIDE3VjdMMTIgMloiIHN0cm9rZT0id2hpdGUiIHN0cm9rZS13aWR0aD0iMiIvPgo8L3N2Zz4=" alt="Playground"/> </a> </div>🔧 Configuration
Basic Setup
{
"mcpServers": {
"Bright Data": {
"command": "npx",
"args": ["@brightdata/mcp"],
"env": {
"API_TOKEN": "your-token-here"
}
}
}
}
Advanced Configuration
{
"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)
}
}
}
}
Environment Variables
| Variable | Description | Default | Example |
|---|---|---|---|
API_TOKEN | Your Bright Data API token (required) | - | your-token-here |
PRO_MODE | Enable all 60+ tools | false | true |
RATE_LIMIT | Custom rate limiting | unlimited | 100/1h, 50/30m |
WEB_UNLOCKER_ZONE | Custom Web Unlocker zone name | mcp_unlocker | my_custom_zone |
BROWSER_ZONE | Custom Browser zone name | mcp_browser | my_browser_zone |
POLLING_TIMEOUT | Timeout for web_data_* tools polling (seconds) | 600 | 300, 1200 |
BASE_TIMEOUT | Request timeout for base tools in seconds (search & scrape) | No limit | 60, 120 |
BASE_MAX_RETRIES | Max retries for base tools on transient errors (0-3) | 0 | 1, 3 |
GROUPS | Comma-separated tool group IDs | - | ecommerce,browser |
TOOLS | Comma-separated individual tool names | - | extract,scrape_as_html |
Notes:
POLLING_TIMEOUTcontrols how long web_data_* tools wait for results. Each second = 1 polling attempt.- Lower values (e.g., 300) will fail faster on slow data collections.
- Higher values (e.g., 1200) allow more time for complex scraping tasks.
📚 Documentation
<div align="center"> <table> <tr> <td align="center"> <a href="https://docs.brightdata.com/mcp-server/overview"> <img src="https://img.shields.io/badge/📖-API_Docs-blue?style=for-the-badge" alt="API Docs"/> </a> </td> <td align="center"> <a href="https://github.com/brightdata-com/brightdata-mcp/blob/main/examples"> <img src="https://img.shields.io/badge/💡-Examples-green?style=for-the-badge" alt="Examples"/> </a> </td> <td align="center"> <a href="https://github.com/brightdata-com/brightdata-mcp/blob/main/CHANGELOG.md"> <img src="https://img.shields.io/badge/📝-Changelog-orange?style=for-the-badge" alt="Changelog"/> </a> </td> <td align="center"> <a href="https://brightdata.com/blog/ai/web-scraping-with-mcp"> <img src="https://img.shields.io/badge/📚-Tutorial-purple?style=for-the-badge" alt="Tutorial"/> </a> </td> </tr> </table> </div>🚨 Common Issues & Solutions
<details> <summary><b>🔧 Troubleshooting Guide</b></summary>❌ "spawn npx ENOENT" Error
Solution: Install Node.js or use the full path to node:
"command": "/usr/local/bin/node" // macOS/Linux
"command": "C:\\Program Files\\nodejs\\node.exe" // Windows
⏱️ Timeouts on Complex Sites
Solution: Increase timeout in your client settings to 180s
🔑 Authentication Issues
Solution: Ensure your API token is valid and has proper permissions
📡 Remote Server Connection
Solution: Check your internet connection and firewall settings
</details>🤝 Contributing
We love contributions! Here's how you can help:
- 🐛 Report bugs
- 💡 Suggest features
- 🔧 Submit PRs
- ⭐ Star this repo!
Please follow Bright Data's coding standards.
📞 Support
<div align="center"> <table> <tr> <td align="center"> <a href="https://github.com/brightdata-com/brightdata-mcp/issues"> <strong>🐛 GitHub Issues</strong><br/> <sub>Report bugs & features</sub> </a> </td> <td align="center"> <a href="https://docs.brightdata.com/mcp-server/overview"> <strong>📚 Documentation</strong><br/> <sub>Complete guides</sub> </a> </td> <td align="center"> <a href="mailto:support@brightdata.com"> <strong>✉️ Email</strong><br/> <sub>support@brightdata.com</sub> </a> </td> </tr> </table> </div>📜 License
MIT © Bright Data Ltd.
<div align="center"> <p> <strong>Built with ❤️ by</strong><br/> <a href="https://brightdata.com"> <img src="https://idsai.net.technion.ac.il/files/2022/01/Logo-600.png" alt="Bright Data" height="120"/> </a> </p> <p> <sub>The world's #1 web data platform</sub> </p> <br/> <p> <a href="https://github.com/brightdata-com/brightdata-mcp">⭐ Star us on GitHub</a> • <a href="https://brightdata.com/blog">Read our Blog</a> </p> </div>
Related MCP servers
Why Medicare Part D restricts a drug, and the exception and appeal path to challenge it
View repository →
SearXNG MCP Server
Self-hosted SearXNG metasearch for MCP clients: web, image, news, video, music and page fetch.
MCP server for SearXNG with engine targeting, multi-page fanout, and HTML→Markdown URL reading.

UK Legislation Changes
Point-in-time amendment history for 506 UK legislation provisions.
Social layer for Claude Code - DMs, presence, games between AI-assisted developers
View repository →Official MCP server for Brilliant Directories — manage members, posts, leads, reviews, and site content via AI.



