Enables programmatic scraping of product information, prices, and inventory data from Amazon.
Allows for the extraction of product listings, pricing, and market data from eBay.
Provides AI-optimized web search results and specialized tools for extracting location and business data from Google Maps.
Facilitates social media data extraction and profile monitoring on Instagram.
Provides a tool to convert any web page content into clean Markdown, optimized for content extraction and AI documentation.
Enables gathering of structured product details and inventory availability from Walmart.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@The Web MCP What's the latest news on AI regulations in the EU right now?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
The Web MCP 是为 AI 助手赋予真正「上网能力」的通道。告别过时回答，也不再出现“我无法访问实时信息”的窘境——只需稳定、顺畅、可用的网络访问。
由全球领先的Bright Data Web 数据平台打造，这个 MCP 服务器确保你的 AI 不再被封锁、限流或被验证码拦住。
Related MCP server: Spider MCP Server
🔍 实时调研——获取最新价格、新闻与实时数据
🛍️ 电商情报——监测产品、价格与库存
📊 市场分析——跟踪竞品与行业趋势
🤖 AI 代理——构建真正能「浏览网页」的智能体
📝 内容创作——为写作获取最新可信的信息
🎓 学术研究——高效汇聚多源公开数据
零门槛使用，只需在你的 MCP 客户端中添加以下 URL：
https://mcp.brightdata.com/mcp?token=YOUR_API_TOKEN_HERE在 Claude Desktop 中设置：
打开：Settings → Connectors → Add custom connector
名称：Bright Data Web
URL：https://mcp.brightdata.com/mcp?token=YOUR_API_TOKEN
点击 “Add”，完成！✨
{
"mcpServers": {
"Bright Data": {
"command": "npx",
"args": ["@brightdata/mcp"],
"env": {
"API_TOKEN": "<your-api-token-here>"
}
}
}
}💡 注意：Pro 模式不包含在免费套餐内，按使用量额外计费。
✅ “特斯拉当前股价是多少？”
✅ “现在东京评分最高的餐厅有哪些？”
✅ “纽约今天的天气预报是什么？”
✅ “本周有哪些电影上映？”
✅ “今天 Twitter 上的热点话题是什么？”注：以下视频展示的是早期版本，新的演示即将上线！🎥
https://github.com/user-attachments/assets/59f6ebba-801a-49ab-8278-1b2120912e33
https://github.com/user-attachments/assets/61ab0bee-fdfa-4d50-b0de-5fab96b4b91d
工具 | 描述 | 适用场景 |
🔍 | 面向 AI 优化的 Web 搜索 | 研究、查证、时事 |
📄 | 将任意网页转为干净的 Markdown | 内容抽取、文档化 |
类别 | 工具 | 描述 |
浏览器控制 |
| 全功能浏览器自动化 |
Web 数据 API |
| 结构化数据抽取 |
电商 | 产品抓取器 | Amazon、eBay、Walmart 等 |
社媒 | 社交抓取器 | Twitter、LinkedIn、Instagram |
地图与本地 | 位置工具 | Google 地图、商家数据 |
无需任何配置，直接体验 Web MCP：
{
"mcpServers": {
"Bright Data": {
"command": "npx",
"args": ["@brightdata/mcp"],
"env": {
"API_TOKEN": "your-token-here"
}
}
}
}{
"mcpServers": {
"Bright Data": {
"command": "npx",
"args": ["@brightdata/mcp"],
"env": {
"API_TOKEN": "your-token-here",
"PRO_MODE": "true", // 启用 60+ 全部工具
"RATE_LIMIT": "100/1h", // 自定义限速
"WEB_UNLOCKER_ZONE": "custom", // 自定义解封 Zone
"BROWSER_ZONE": "custom_browser" // 自定义浏览器 Zone
}
}
}
}解决：安装 Node.js，或使用 node 的完整路径：
"command": "/usr/local/bin/node" // macOS/Linux
"command": "C:\\Program Files\\nodejs\\node.exe" // Windows解决：在客户端设置中将超时提高到 180s
解决：确认 API Token 有效且具备相应权限
解决：检查网络与防火墙设置
我们欢迎各种形式的贡献：
请遵循 Bright Data 的代码规范。
MIT © Bright Data Ltd.
Scrape a single webpage URL with advanced options for content extraction and get back the results in MarkDown language. This tool can unlock any webpage even if it uses bot detection or CAPTCHA.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It discloses key behavioral traits: advanced content extraction, ability to handle bot detection/CAPTCHA, and Markdown output format. However, it lacks details on rate limits, error handling, authentication needs, or what 'advanced options' entail, which are important for a scraping tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences that efficiently convey purpose and key capabilities without waste. It's front-loaded with the main function and follows with the unlocking feature. A minor improvement could be integrating the Markdown output more seamlessly, but overall it's well-structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no annotations, 1 parameter with 0% schema coverage, and no output schema, the description is moderately complete. It covers the core purpose and some behavioral aspects but lacks details on parameters, error cases, or output structure. For a tool with potential complexity (handling bot detection), more context would be helpful.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 1 parameter (url) with 0% description coverage, so the description must compensate. It clarifies that the url is for a 'single webpage' and implies it's for scraping, adding meaningful context beyond the schema's URI format. However, it doesn't detail URL constraints or what 'advanced options' might be, keeping it from a perfect score.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool scrapes a single webpage URL with advanced content extraction and returns results in Markdown. It specifies the verb (scrape), resource (webpage), and output format (Markdown), which distinguishes it from HTML-based scraping siblings. However, it doesn't explicitly differentiate from all siblings like 'extract' or domain-specific tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for webpages with bot detection or CAPTCHA ('unlock any webpage'), suggesting when this tool might be preferred over simpler scraping tools. However, it doesn't explicitly state when NOT to use it or name specific alternatives among the many sibling tools, leaving some ambiguity.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Scrape multiple webpages URLs with advanced options for content extraction and get back the results in MarkDown language. This tool can unlock any webpage even if it uses bot detection or CAPTCHA.
| Name | Required | Description | Default |
|---|---|---|---|
| urls | Yes | Array of URLs to scrape (max 10) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It discloses key behavioral traits: batch processing of multiple URLs (implied by 'multiple webpages'), advanced content extraction, output in MarkDown, and ability to bypass bot detection/CAPTCHA. However, it lacks details on rate limits, error handling, authentication needs, or what 'advanced options' entail, leaving gaps for a mutation-like operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise with two sentences that efficiently convey core functionality. The first sentence covers purpose and output, while the second adds behavioral context. No wasted words, though it could be more structured by explicitly separating features from limitations.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no annotations, no output schema, and a single parameter with full schema coverage, the description is moderately complete. It covers what the tool does and key capabilities (bypassing bot detection), but lacks details on return values, error cases, or performance constraints, which are important for a web scraping tool with potential complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, with the schema fully documenting the 'urls' parameter (array of URIs, min 1, max 10). The description adds no parameter-specific semantics beyond implying batch processing through 'multiple webpages URLs.' Since schema coverage is high, baseline 3 is appropriate as the description doesn't significantly enhance parameter understanding.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Scrape multiple webpages URLs with advanced options for content extraction and get back the results in MarkDown language.' It specifies the verb (scrape), resource (webpages), and output format (MarkDown). However, it doesn't explicitly differentiate from sibling tools like scrape_as_markdown, which might be for single URLs, so it misses full sibling distinction.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. It mentions 'advanced options for content extraction' and ability to 'unlock any webpage even if it uses bot detection or CAPTCHA,' but doesn't specify when to choose this over scrape_as_markdown or search_engine tools. No explicit alternatives or exclusions are provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Scrape search results from Google, Bing or Yandex. Returns SERP results in markdown (URL, title, description)
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | ||
| engine | No | ||
| cursor | No | Pagination cursor for next page |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It mentions scraping and return format (SERP results in markdown), but lacks critical behavioral details: whether this requires authentication, rate limits, potential blocking risks, pagination behavior beyond the cursor parameter, or error handling. For a scraping tool with zero annotation coverage, this leaves significant gaps in understanding how the tool behaves.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Perfectly concise and front-loaded: two sentences that directly state what the tool does and what it returns. Every word earns its place with zero redundancy or unnecessary elaboration.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of web scraping (which involves network calls, potential failures, and structured data extraction), no annotations, and no output schema, the description is incomplete. It doesn't cover error conditions, rate limits, authentication needs, or detailed output structure beyond 'markdown'. For a tool with 3 parameters and significant behavioral implications, more context is needed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 33% (only cursor has a description). The description adds minimal parameter context: it implies 'engine' selects between Google/Bing/Yandex (though the enum already shows this) and 'query' is for search terms. However, it doesn't explain parameter interactions, format requirements for query, or how cursor works with the returned results. With low schema coverage, the description provides some but insufficient compensation.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Scrape search results from Google, Bing or Yandex' specifies the verb (scrape) and resource (search results from specific engines). It distinguishes from many siblings that scrape specific websites (e.g., web_data_amazon_product) but doesn't explicitly differentiate from generic scraping tools like scrape_as_html or scrape_as_markdown.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives. It doesn't mention when to choose search_engine over other scraping tools like scrape_as_html for the same search engines, or when to use it versus specialized web_data tools for specific platforms. The description provides no context about use cases or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Run multiple search queries simultaneously. Returns JSON for Google, Markdown for Bing/Yandex.
| Name | Required | Description | Default |
|---|---|---|---|
| queries | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden. It discloses output format differences (JSON for Google, Markdown for Bing/Yandex), which is useful behavioral context. However, it doesn't mention rate limits, authentication needs, error handling, or what 'simultaneously' entails (parallel vs sequential). For a batch operation tool, this leaves significant gaps in understanding its behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Extremely concise with two sentences that each add value. First sentence states core functionality, second sentence provides critical output format information. No wasted words, perfectly front-loaded with essential information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no annotations, 0% schema description coverage, and no output schema, the description is incomplete for a batch search tool. It covers purpose and output formats but misses parameter explanations, error conditions, rate limits, and detailed behavioral traits. For a tool handling multiple search engines with different output formats, more context is needed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate. It adds some meaning by mentioning engine-specific output formats, which relates to the 'engine' parameter. However, it doesn't explain the 'queries' array structure, 'cursor' parameter purpose, or the 1-10 item limit. The description provides partial context but doesn't fully compensate for the schema's lack of descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Run multiple search queries simultaneously' specifies the verb and resource. It distinguishes from siblings like 'search_engine' (likely single query) and 'scrape_as_markdown'/'scrape_batch' (different operations), though not explicitly named. However, it doesn't fully differentiate from 'scrape_batch' which might also handle multiple items.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool versus alternatives is provided. The description mentions output formats for different engines, but doesn't state when to choose this batch tool over single-query tools like 'search_engine' or scraping tools. Usage context is implied but not clearly defined.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
scrape_as_markdownscrape_batchsearch_enginesearch_engine_batchScored across 4 tools
Each tool has a clearly distinct purpose: scrape_as_markdown handles single webpage scraping, scrape_batch handles multiple webpages, search_engine scrapes single search queries, and search_engine_batch handles multiple search queries. There is no overlap in functionality, making tool selection straightforward for an agent.
All tool names follow a consistent snake_case pattern with clear verb_noun structures: scrape_as_markdown, scrape_batch, search_engine, and search_engine_batch. The naming is predictable and aligns well with the actions each tool performs.
With 4 tools, the server is well-scoped for web scraping and search functionality. Each tool earns its place by covering distinct aspects of the domain: single and batch operations for both webpage scraping and search engine queries, avoiding bloat while providing essential coverage.
The tool set covers core web scraping and search operations effectively, including single and batch modes. A minor gap exists in lacking tools for more advanced interactions like form submission or dynamic content handling, but the provided tools support key workflows without dead ends.
Web search, browser automation, scraping, crawling and CAPTCHA solving for AI agents.
Direct access to 60+ scraping and search tools. Extract structured data from Google (Search, Maps, Trends), Amazon, Airbnb, Social Media, and any web page directly into your AI agent.
Live web access for agents: scrape, SERP search, crawl/map, 74 collectors, datasets, proxies.
Web data tools for AI agents: pages as markdown, search, maps, commerce, jobs, AI answers.
