Brightdata MCPサーバー
- GitHubスター 2716
- 2026年11月5日更新
Brightdata Mcp MCPは、Claude CodeやCursorなどのクライアントから、コーディングエージェントがBrightdata Mcpのツールを呼び出せるようにするModel Context Protocolサーバーです。
Brightdata MCPとは?
Brightdata Mcpは、Claude Code、Cursor、CodexなどのMCPクライアントを、Model Context Protocol経由でBrightdata Mcpプラットフォームの機能に接続するMCPサーバーです。Bright DataのWeb MCPサーバーで、AIエージェントがWebを検索、抽出、ナビゲートできるようにします。開発者は、スキルのラッパーだけに頼らず、MCP型のSkillselionリスティングを使うことで、Brightdata Mcpブランドについてインストールのメタデータとツールの範囲を正確に保てます。実装や運用の作業でライブのプラットフォームの文脈が必要なとき、エージェントがダッシュボードを何度も切り替えずにBrightdata Mcpのツールを呼び出せます。セットアップは、brightdata/brightdata-mcpに添えられたパブリッシャー提供のMCPクライアント設定に従います。リモートまたはローカルのサーバー向けの認証やトランスポートの詳細も、そこに記載されています。まず読み取り系のツール呼び出しを優先し、対象環境を確認したうえで、認証情報はエージェントのシークレットストアで管理してください。本番で変更を伴う操作を有効にする前に、Security Auditsパネルを確認し、書き込みスコープを制限してください。CLIやダッシュボードのワークフローを補完するものであり、機微なアカウントのアクセス制御、変更レビュー、シークレット管理を代替するものではありません。
- Brightdata Mcp用のMCP型リスティング
- Claude Code、Cursor、CodexをMCP経由でBrightdata Mcpに接続
- リポジトリはbrightdata/brightdata-mcp
- ライブのプラットフォーム操作をエージェントのセッション内で完結
- 本番で書き込む前に、認証スコープの確認が必要
数字で見るBrightdata Mcp
- 2026年11月9日時点のデータ(Skillselionカタログ同期)
claude mcp add --env API_TOKEN=YOUR_API_TOKEN --env WEB_UNLOCKER_ZONE=YOUR_WEB_UNLOCKER_ZONE --env BROWSER_ZONE=YOUR_BROWSER_ZONE --env PRO_MODE=YOUR_PRO_MODE --env GROUPS=YOUR_GROUPS --env TOOLS=YOUR_TOOLS --env POLLING_TIMEOUT=YOUR_POLLING_TIMEOUT --env BASE_TIMEOUT=YOUR_BASE_TIMEOUT --env BASE_MAX_RETRIES=YOUR_BASE_MAX_RETRIES brightdata-mcp -- npx -y @brightdata/mcpBrightdata Mcpのバッジを追加する
このMCPサーバーがSkillselionに掲載されていることを開発者に示せます。READMEに貼り付けてください。
埋め込みコードを取得
| GitHubスター | ★ 2716 |
|---|---|
| パッケージ | @brightdata/mcp |
| トランスポート | STDIO |
| 認証 | 必要 |
| 最終更新 | 2026年11月5日 |
| リポジトリ | brightdata/brightdata-mcp ↗ |
ユースケースと機能
ダッシュボードを何度も切り替えずに、コーディングエージェントにBrightdata Mcpへのライブアクセスを与えるにはどうすればよいですか?
コーディングエージェントをBrightdata Mcpに接続し、エディターを離れずに、実装中にプラットフォームのツールを呼び出せるようにします。
Brightdata MCPはどんな人に向いていますか?
Brightdata Mcpを使っていて、エージェント主導でプラットフォームを操作したい開発者に向いています。
見送ったほうがよい場合: Brightdata Mcpを使っていない場合や、MCPアクセスを承認できない場合は見送ってください。
Brightdata MCPは何を生成しますか?
エージェントのセッション内で、Brightdata Mcpに認証済みのMCPツールとしてアクセスできます。
- 登録済みのBrightdata Mcp MCP
- エージェントから呼び出せるツール
- @brightdata/mcpのレジストリバージョンは2.9.5
- registry.npmjs.orgからのstdio npmトランスポート
- ツールの動作を拡張するために設定できるPRO_MODEのブール値
Brightdata Mcpで何ができますか?
- ユースケース
- API開発 · オーケストレーション
Brightdata Mcpのドキュメントが説明する機能
Bright Data's Web MCP server enabling AI agents to search, extract & navigate the web
Brightdata McpのREADMEには何が書かれていますか?
README.md
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 credits/month FREE
No credit card required · Auto-renews monthly · 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
🌟 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.
| ✅ Works with Any LLM Claude, GPT, Gemini, Llama |
🛡️ Never Gets Blocked Enterprise-grade unblocking |
🚀 5,000 Free Credits Monthly · No card needed |
⚡ Zero Config Works out of the box |
🎯 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:
📡 Use our hosted server - No installation needed!
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! ✨
Run locally on your machine
{
"mcpServers": {
"Bright Data": {
"command": "npx",
"args": ["@brightdata/mcp"],
"env": {
"API_TOKEN": "<your-api-token-here>"
}
}
}
}
🚀 Pricing & Modes
| ⚡ Rapid Mode (Free tier) | 💎 Pro Mode | 🔧 Custom Mode |
|---|---|---|
$0/month5,000 credits ✅ Web Search Default Mode
|
Pay-as-you-goEverything in rapid plus 60+ tools ✅ Browser Control |
Usage-basedPick the tools you need ✅ Combine tool groups GROUPS="browser"TOOLS="scrape_as_html"
|
💡 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.
| 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 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
| 🔍 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 |
🎯 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
Note: These videos show earlier versions. New demos coming soon! 🎥
View Demo Videos
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
🔧 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)
Click to see all Pro tools
| 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 |
🎮 Try It Now!
🧪 Online Playground
Try the Web MCP without any setup:
🔧 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
🚨 Common Issues & Solutions
🔧 Troubleshooting Guide
❌ "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
🤝 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
|
🐛 GitHub Issues Report bugs & features |
📚 Documentation Complete guides |
✉️ Email support@brightdata.com |
📜 License
MIT © Bright Data Ltd.
GitHubスター順に並べたClaude Code MCPサーバーの一覧はこちらです。
Brightdata MCPに関連するMCPサーバーは?
Brightdata Mcpは類似ツールとどう違いますか?
スキルのラッパーよりも、MCP型のBrightdata Mcpリスティングをおすすめします。
Brightdata MCPのよくある質問
Brightdata MCP MCPはどんな人向けですか?
Brightdata MCPを使っていて、コーディングエージェントからMCP経由でプラットフォームのツールを呼び出したい開発者向けです。
Brightdata MCP MCPはどんなときに使いますか?
実装や運用のタスクで、エージェントの中でBrightdata MCPのライブの文脈が必要なときに使います。
Brightdata MCP MCPは安全にインストールできますか?
本番で書き込む前に、Security Auditsパネルを確認し、スコープを制限してください。