de en es ja ko ru zh

Bright Data MCP

Name: Bright Data MCP
Author: brightdata

Official

by brightdata

Overview Schema Source Related Servers Score Discussions Admin

JavaScript

Hybrid

🌟 개요

The Web MCP는 AI 어시스턴트에게 진정한 웹 기능을 제공하는 관문입니다. 더 이상 오래된 응답은 없습니다. "실시간 정보에 액세스할 수 없습니다"라는 말도 이제 끝입니다. 실제로 작동하는 원활하고 신뢰할 수 있는 웹 액세스를 경험하세요.

세계 1위 웹 데이터 플랫폼인 Bright Data가 구축한 이 MCP 서버는 AI가 절대 차단되거나, 속도 제한에 걸리거나, CAPTCHA를 마주하지 않도록 보장합니다.

Related MCP server: MCP Fetch

🎯 추천 대상

🔍 실시간 조사 - 현재 가격, 뉴스 및 라이브 데이터 확인
🛍️ 이커머스 인텔리전스 - 제품, 가격 및 재고 모니터링
📊 시장 분석 - 경쟁사 및 업계 동향 추적
🤖 AI 에이전트 - 실제로 웹을 탐색할 수 있는 에이전트 구축
💻 코딩 에이전트 - npm/PyPI 패키지, 버전 및 README를 실시간으로 조회
🧠 GEO 및 브랜드 가시성 - ChatGPT, Grok, Perplexity가 귀하의 브랜드를 어떻게 인식하는지 확인
📝 콘텐츠 제작 - 최신 정보를 활용한 글쓰기
🎓 학술 연구 - 여러 소스에서 효율적으로 데이터 수집

⚡ 빠른 시작

설정 마법사 사용:

GIF for day2

설정이 필요 없는 사용자에게 적합합니다. MCP 클라이언트에 이 URL을 추가하기만 하면 됩니다:

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

Claude Desktop 설정:

이동: 설정 → 커넥터 → 사용자 지정 커넥터 추가
이름: Bright Data Web
URL: https://mcp.brightdata.com/mcp?token=YOUR_API_TOKEN
"추가"를 클릭하면 완료됩니다! ✨

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

🚀 가격 및 모드

💡 참고: Pro 모드는 무료 티어에 포함되어 있지 않으며 사용량에 따라 추가 요금이 발생합니다.

🧠 고급 도구 선택

GROUPS를 사용하면 선별된 도구 번들을 활성화할 수 있습니다. ecommerce,browser와 같이 쉼표로 구분된 그룹 ID를 사용하세요.
TOOLS는 선택한 그룹 외에 명시적인 도구 이름을 추가합니다.
모드 우선순위: PRO_MODE=true (모든 도구) → GROUPS / TOOLS (화이트리스트) → 기본 Rapid 모드 (기본 툴킷).
항상 활성화된 기본 도구: search_engine, search_engine_batch, scrape_as_markdown, scrape_batch, discover.
그룹 ID custom은 예약되어 있습니다. 맞춤형 선택을 하려면 TOOLS를 사용하세요.

Claude Desktop 예시

{
  "mcpServers": {
    "Bright Data": {
      "command": "npx",
      "args": ["@brightdata/mcp"],
      "env": {
        "API_TOKEN": "<your-api-token-here>",
        "GROUPS": "browser,advanced_scraping",
        "TOOLS": "extract"
      }
    }
  }
}

코딩 에이전트 예시 (Claude Code / Cursor / Windsurf)

코딩 에이전트에게 실시간 패키지 인텔리전스를 제공하세요. 스크래핑 없이 npm 및 PyPI에서 최신 버전, README, 의존성 및 메타데이터를 가져옵니다:

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

✨ 기능

🔥 핵심 역량

🎯 바로 작동하는 예시 쿼리

✅ "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"

🎬 데모

참고: 이 영상들은 이전 버전을 보여줍니다. 새로운 데모가 곧 제공될 예정입니다! 🎥

기본 웹 검색 데모

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

고급 스크래핑 데모

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

📺 YouTube에서 더 많은 튜토리얼 보기 →

🔧 사용 가능한 도구

⚡ Rapid 모드 도구 (기본 - 무료)

도구	설명	사용 사례
🔍 `search_engine`	AI 최적화 결과가 포함

Available Tools

5 tools

discoverA

Read-only

Search the web and rank results by AI-driven relevance. Returns scored results with title, description, and URL. Supports intent-based ranking, geo-targeting, date filtering, and keyword filtering.

ParametersJSON Schema

Name	Required	Description
`city`	No	City for localized results (e.g., "New York", "Berlin")
`query`	Yes	The search query
`intent`	No	Describes the specific goal of the search to help the AI evaluate and rank result relevance.If not provided, the query string is used as the intent
`country`	No	2-letter ISO country code for localized results (e.g., "US", "GB", "DE")
`end_date`	No	Only content updated until this date (YYYY-MM-DD)
`language`	No	Language code (e.g., "en", "es", "fr")
`start_date`	No	Only content updated from this date (YYYY-MM-DD)
`num_results`	No	Exact number of search results to return
`filter_keywords`	No	Keywords that must appear in search results
`remove_duplicates`	No	Remove duplicate results (default: true)

TDQS

A3.9/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations provide readOnlyHint (true) and openWorldHint (true), confirming safe read from external web. The description adds value by detailing AI-driven ranking, intent-based ranking, geo-targeting, and filtering, which are behavioral traits not fully captured by annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences: first states purpose and return type, second lists features. No fluff, front-loaded, and every sentence adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 10 parameters and no output schema, the description covers key aspects (scored results, features) but lacks details on default number of results, scoring mechanics, or error handling. Adequate but with gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so baseline is 3. The description adds minimal extra meaning by grouping features (e.g., 'geo-targeting' maps to city/country) but does not elaborate on parameter usage beyond schema descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool performs web search with AI-driven relevance ranking and returns scored results with title, description, and URL. It lists supported features (intent, geo, date, keyword), distinguishing it from siblings like search_engine and scrape tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage through features but does not explicitly state when to use this tool vs alternatives like search_engine or scrape_as_markdown. No when-not-to 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_as_markdownB

Read-only

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.

ParametersJSON Schema

Name	Required	Description	Default
`url`	Yes

TDQS

B3.2/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate read-only and open-world behavior. The description adds a key behavioral claim: the ability to bypass bot detection and CAPTCHA, which is valuable information not covered by annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences with no wasted words. The claim about unlocking any webpage is front-loaded but could be more precise about scope.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a single-parameter tool with no output schema, the description covers the main purpose and a key feature (bot detection bypass). However, it lacks details on return structure, error handling, or rate limits.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, and the description only repeats 'webpage URL' without adding format or constraints beyond the schema's `format: uri`. No detail on the single parameter's meaning.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

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 and returns MarkDown, distinguishing it from siblings like scrape_batch. However, it mentions 'advanced options' that are not reflected in the input schema, slightly reducing clarity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for single URL scraping with bot detection bypass, but does not explicitly state when to use vs. siblings (e.g., scrape_batch for multiple URLs) or list any prerequisites or limitations.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

scrape_batchA

Read-only

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.

ParametersJSON Schema

Name	Required	Description	Default
`urls`	Yes	Array of URLs to scrape (max 5)

TDQS

A4.2/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description adds value beyond annotations by noting MarkDown output and the ability to unlock webpages with bot detection/CAPTCHA. No contradictions with readOnlyHint and openWorldHint.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with core function and output format, no unnecessary words. Efficient and to the point.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given one parameter and no output schema, the description covers the main function and key capability. The vague phrase 'advanced options for content extraction' is a minor gap, but otherwise complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% for the single parameter 'urls', so baseline is 3. The description does not add significant meaning beyond the schema, merely restating 'multiple webpages URLs'.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb (scrape), resource (webpages), and output format (MarkDown). It distinguishes from siblings like scrape_as_markdown by specifying batch operation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies use for multiple URLs and mentions bypassing bot detection, providing clear context. However, it lacks explicit when-not-to-use or alternative tool guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

search_engineB

Read-only

Scrape search results from Google, Bing or Yandex. Returns SERP results in JSON or Markdown (URL, title, description),Ideal forgathering current information, news, and detailed search results.

ParametersJSON Schema

Name	Required	Description	Default
`query`	Yes
`cursor`	No	Pagination cursor for next page
`engine`	No		google
`geo_location`	No	2-letter country code for geo-targeted results (e.g., "us", "uk")

TDQS

B3.4/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint and openWorldHint. The description adds output format and fields but does not disclose rate limits, auth requirements, or limitations. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences with a typo ('forgathering') and missing punctuation ('results,Ideal'). Could be more concise and better structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 4 parameters and no output schema, the description lacks explanation of pagination, engine selection, and geo-targeting. Output format is mentioned but not how to use the tool effectively.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 50% (cursor and geo_location have descriptions). The tool description does not elaborate on any parameters, failing to compensate for undocumented query and engine parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool scrapes search results from Google, Bing, or Yandex and returns SERP data in JSON/Markdown. It distinguishes itself from sibling tools like search_engine_batch (batch variant) and scrape_as_markdown (scrapes a single page).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description indicates it is ideal for gathering current information, news, and detailed search results but does not explicitly contrast with siblings or specify when to avoid using it. No mention of alternatives or prerequisites.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

search_engine_batchA

Read-only

Run multiple search queries simultaneously. Returns JSON for Google, Markdown for Bing/Yandex.

ParametersJSON Schema

Name	Required	Description	Default
`queries`	Yes

TDQS

A3.7/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and openWorldHint=true. The description adds that output format differs by engine (JSON for Google, Markdown for Bing/Yandex), which is useful but does not disclose other behavioral details like rate limits or authentication needs.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, front-loading purpose and format differences. Every sentence adds value with no wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity (batch, multiple engines, optional parameters, varying output formats), the description lacks essential details about how to structure queries and interpret results. No output schema exists to compensate.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema description coverage is 0%, and the tool description provides no explanation of the parameters (e.g., that queries is an array of objects with fields like cursor, engine, geo_location). The agent must rely solely on the schema, which is insufficient for correct invocation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it runs multiple search queries simultaneously, which is a specific verb+resource. It distinguishes from sibling tools like search_engine (single query) and scrape tools by being a batch search operation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for batching multiple queries, but lacks explicit when-to-use vs when-not-to-use or alternatives. It is clear enough to guide the agent to use this over search_engine for multiple queries.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

5 tool updatesv2.9.3May 11, 2026
- Addeddiscover
- Addedscrape_as_markdown
- Addedscrape_batch
- Addedsearch_engine
- Addedsearch_engine_batch

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.6/5.0

Disambiguation4/5

Most tools have distinct purposes: discover for AI-ranked web search, scrape for webpage content, and search_engine for SERP results. However, discover and search_engine both involve search, potentially causing confusion.

Naming Consistency3/5

Naming mixes patterns: 'discover' is a single verb, 'scrape_as_markdown' is a phrase, 'search_engine' is a noun. Inconsistent but still readable.

Tool Count4/5

With 5 tools covering web search, scraping (single/batch), and engine search (single/batch), the count is appropriate for a focused data extraction tool.

Completeness4/5

Covers key data extraction needs: AI search, webpage scraping, and SERP scraping. Minor gap: no tool for updating or deleting data, but that is outside typical scope.

Maintenance

ActivityMaintained

ResponsivenessWithin a week

Resources

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

hithereiamaliff-mcp-nextcloudOAuth
ai.smithery
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Cloud Storage File Systems Workplace & Productivity
237
Bright Data A
io.github.pipeworx-io
Bright Data MCP — Bright Data Web Unlocker + SERP API (brightdata.com)
Web Scraping Browser Automation Search
332
mcp COAuth
com.wix
A Model Context Protocol server for Wix AI tools
Developer Tools Content Management Systems App Automation
216
scrapeless-mcp-server
io.github.scrapeless-ai
Web search, browser automation, scraping, crawling and CAPTCHA solving for AI agents.
1168

Related MCP Servers

MCP Web Research Server
Browser Automation Web Scraping Search
mzxrai
A
license
B
quality
F
maintenance
A Model Context Protocol (MCP) server for web research. Bring real-time info into Claude and easily research any topic.
Updated 2 years ago (2024-12-18 03:38 UTC)
3
1,202
300
MIT
MCP Fetch
Browser Automation Image & Video Processing Web Scraping
JeremyNixon
A
license
A
quality
D
maintenance
Model Context Protocol server that enables Claude Desktop (or any MCP client) to fetch web content and process images appropriately.
Updated 2 years ago (2025-01-12 09:51 UTC)
1
170
MIT
MCP Web Research Server
Browser Automation Web Scraping Search
chuanmingliu
A
license
B
quality
D
maintenance
A Model Context Protocol server that enables Claude to perform web research by integrating Google search, extracting webpage content, and capturing screenshots.
Updated 2 years ago (2025-03-01 16:08 UTC)
1
3
1,202
20
MIT
MCP Web Research Server
Web Scraping Search Browser Automation
PhialsBasement
A
license
A
quality
C
maintenance
A Model Context Protocol server that enables Claude to perform web research by integrating Google search, extracting webpage content, and capturing screenshots in real-time.
Updated 10 months ago (2025-11-09 23:00 UTC)
4
1,202
9
MIT

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/brightdata/brightdata-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server