1. Home
  2. Servers
  3. Search & Web Data
  4. Bright Data Web MCP

Server profile

Bright Data Web MCP

Give AI assistants live web search, page extraction, and optional browser automation through Bright Data. Tool groups also provide structured datasets, package information, and AI brand-visibility queries.

View repositoryInstall & configure

Server facts

Bright Data Web MCP

Tech

Runtime / language
node
Transports
stdio
Remote available
No
Authentication
Not specified

Activity

GitHub stars
2,678
Last commit
Data as of

Tags

  • Browser Automation
  • Package Metadata
  • Web Scraping
  • Web Search

Overview

Bright Data Web MCP connects assistants to web search and extraction services operated by Bright Data. Its base toolkit searches the web, retrieves pages as Markdown, and offers intent-ranked discovery. Batch variants support work across multiple searches or pages. The README positions these capabilities for current research, price monitoring, competitor analysis, and content preparation. Users can connect to a hosted endpoint or run the MCP process locally with an API token, making the same service available to different kinds of MCP clients.

Additional capabilities are organized into selectable groups rather than requiring every tool to be exposed. These include browser control, retail datasets, social content, finance, travel, and business information. A code group supplies npm and PyPI package details, while a GEO group queries ChatGPT, Grok, and Perplexity for brand-related insights. The default Rapid mode has a monthly credit allowance; Pro mode enables the larger toolkit and incurs usage charges. Custom selection narrows the surface through group and tool settings but does not bypass paid eligibility. Browser automation is not part of the free base mode. Configuration also includes request limits, timeouts, and custom zones. Consequently, choosing this server involves both selecting relevant tools and understanding which Bright Data services consume credits for the intended workflow.

Install & configure

Requirements

  • Node.js with npx for local execution
  • A Bright Data account and API token
  • An MCP-compatible client
Documented launch / install command
npx @brightdata/mcp

This configuration uses the local process. A hosted endpoint is also documented. Rapid mode is the default; optional groups and Pro tools can change usage costs.

Config file · macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

Windows: %APPDATA%\Claude\claude_desktop_config.json

Use Settings → Developer → Edit Config when available. Do not assume a Linux configuration path; check the client documentation for your platform. Remote servers use the app’s connector flow when supported, not the local stdio file shown here. Merge this example with existing settings; do not overwrite unrelated servers.

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

Read the Claude Desktop setup guide

Config file · Project: .cursor/mcp.json

User: ~/.cursor/mcp.json

The project path is relative to the workspace root. The tilde denotes your user home directory. Use Cursor’s MCP settings to confirm which configuration and scope your installed version is reading. Merge this example with existing settings; do not overwrite unrelated servers.

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

Read the Cursor setup guide

Config file · Workspace: .vscode/mcp.json

For user scope, use the “MCP: Open User Configuration” command if available. Do not guess a user configuration path across operating systems, profiles, containers, or remote workspaces; check the client documentation. Merge this example with existing settings; do not overwrite unrelated servers.

VS Code configuration
{
  "servers": {
    "brightdata-mcp": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "@brightdata/mcp"
      ],
      "env": {
        "API_TOKEN": "<your Bright Data API token>"
      }
    }
  }
}

Read the VS Code setup guide

Config file · macOS/Linux: ~/.codeium/windsurf/mcp_config.json

Windows: %USERPROFILE%\.codeium\windsurf\mcp_config.json

Open the MCP configuration through Windsurf’s settings when possible to confirm the active file. Paths can differ in managed or future releases; check the client documentation if this location is not present. Merge this example with existing settings; do not overwrite unrelated servers.

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

Read the Windsurf setup guide

Config file · Project scope: .mcp.json at the repository root

The project file uses mcpServers. For user scope, use claude mcp add --scope user rather than assuming .mcp.json in your home directory is the user configuration. Check the client documentation for managed settings and storage details. Merge this example with existing settings; do not overwrite unrelated servers.

Claude Code configuration
{
  "mcpServers": {
    "brightdata-mcp": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "@brightdata/mcp"
      ],
      "env": {
        "API_TOKEN": "<your Bright Data API token>"
      }
    }
  }
}

Read the Claude Code setup guide

Examples are translated from the published configuration. Supply your own credentials and verify requirements in the upstream README. Remote connectors are shown only where a supported configuration format is known.

Tools

Source: repository README. Tool descriptions are a documented snapshot, not a live capability check.

ToolWhat it does
search_engineSearch the live web for results suitable for an assistant's research workflow.
search_engine_batchRun multiple web searches as a batch.
scrape_as_markdownExtract a web page into Markdown content.
scrape_batchRetrieve content from multiple pages in one batch workflow.
discoverFind web results ranked against the intent of a research query.
scrape_as_htmlRetrieve HTML through an explicitly selected scraping tool.
extractUse the advanced scraping group for AI-assisted extraction.
scraping_browser_snapshotInspect the state of a remotely controlled browser.
scraping_browser_click_refClick a referenced element in the remote browser.
scraping_browser_screenshotCapture an image from the remote browser.
web_data_amazon_productRetrieve structured Amazon product information.
web_data_walmart_productRetrieve structured Walmart product information.
web_data_google_shoppingAccess Google Shopping dataset information.
web_data_linkedin_postsRetrieve structured LinkedIn post data.
web_data_tiktok_postsRetrieve structured TikTok post data.
web_data_youtube_videosRetrieve structured YouTube video information.
web_data_yahoo_finance_businessAccess company information from Yahoo Finance.
web_data_crunchbase_companyRetrieve Crunchbase company data.
web_data_zoominfo_company_profileAccess structured ZoomInfo company profiles.
web_data_zillow_properties_listingRetrieve Zillow property listing data.
web_data_github_repository_fileRetrieve repository file data from GitHub.
web_data_reuter_newsAccess the documented Reuters news dataset tool.
web_data_google_play_storeRetrieve Google Play store data.
web_data_apple_app_storeRetrieve Apple App Store data.
web_data_booking_hotel_listingsAccess Booking hotel listing information.
web_data_chatgpt_ai_insightsQuery ChatGPT for structured AI insights and brand visibility research.
web_data_grok_ai_insightsQuery Grok for AI insights useful in brand visibility research.
web_data_perplexity_ai_insightsQuery Perplexity for sourced AI answers and brand visibility research.
web_data_npm_packageLook up npm package versions, documentation, and dependency metadata.
web_data_pypi_packageLook up Python package versions and project information from PyPI.

Names, permissions, and defaults can change. Check the current upstream documentation before granting access.

Use cases

  • Research current web information and extract readable page content.
  • Monitor product details and prices across retail datasets.
  • Look up npm or PyPI versions, metadata, and READMEs.
  • Compare AI-generated brand mentions across supported LLM services.

Strengths

  • Supports hosted access and a documented local npx configuration.
  • Tool groups let users limit the capabilities exposed to an assistant.
  • Combines search, scraping, structured datasets, and optional browser control.

Limitations

  • Requires a Bright Data API token.
  • Browser automation and Pro capabilities incur usage charges.
  • Requests stop after the free credit pool is exhausted unless funds are available.

Frequently asked questions

The README describes 5,000 credits per month without a credit card. Unused credits do not carry over.

No. Browser control belongs to the paid capabilities rather than the Rapid base toolkit.

Yes. Bright Data documents a hosted MCP endpoint authenticated using your API token.

Yes. GROUPS selects bundles and TOOLS adds named tools. Custom selection does not remove Pro eligibility requirements.

Independent listing, not an affiliation or security review. Grant the least access needed and verify the upstream instructions before running code.

Related MCP servers

Firecrawl MCP Server

Search & Web Data

Firecrawl MCP connects AI agents to web search, scraping, crawling, and live browser interaction. It offers hosted access or a local server for collecting structured web context and running research tasks.

nodestdio7,615 GitHub stars

Tavily MCP Server

Search & Web Data

Tavily MCP Server connects AI clients to web search, page extraction, site mapping, and crawling. Run it locally with an API key or connect to the hosted service using API-key or OAuth authentication.

nodestdio2,433 GitHub stars

AgentQL MCP Server

Search & Web Data

AgentQL MCP Server extracts structured JSON from a web page using a natural-language description of the desired fields. It provides one focused extraction tool for MCP assistants.

nodestdio181 GitHub stars

Exa MCP Server

Search & Web Data

Exa MCP Server gives AI assistants web search and readable page retrieval, with optional advanced search and agent research tools. It supports hosted connections and a local npm package for research and coding context.

nodestdio5,138 GitHub stars

Perplexity API Platform MCP Server

Search & Web Data

The Perplexity API Platform MCP Server gives assistants web search, conversational answers, research, and reasoning tools. It connects to Perplexity’s Search API and Sonar models through local stdio or an HTTP deployment.

nodestdio2,573 GitHub stars

ArXiv MCP Server

Search & Web Data

Search arXiv, download papers, and read their contents through an AI assistant. Local storage and research prompts support repeatable literature review and paper analysis.

pythonstdio3,221 GitHub stars

DuckDuckGo Search MCP Server

Search & Web Data

Give MCP assistants DuckDuckGo search and webpage text retrieval. It suits research workflows that need regional results, readable page content, and configurable filtering.

pythonstdio1,538 GitHub stars

Yargı MCP

Search & Web Data

Search Turkish court and regulatory decisions from MCP-compatible assistants. Yargı MCP retrieves decision texts as Markdown and offers both local execution and a hosted streamable HTTP endpoint.

pythonstdio1,007 GitHub stars