Bright Data Web MCP Server for Claude

Safety notes

This server sends web searches, URLs, scraping targets, browser actions, package names, and dataset requests to Bright Data APIs.
Review website terms, robots policies, rate limits, jurisdictional requirements, and internal scraping policies before automating collection.
`PRO_MODE`, browser automation groups, data-product groups, and batch tools can increase cost, request volume, and operational impact.
The server can create or use Bright Data zones through API calls; review account permissions and zone settings before running it with broad API tokens.
Use `RATE_LIMIT`, group selection, and explicit tool allowlists to keep agent-driven browsing and scraping bounded.

Privacy notes

Bright Data API tokens must stay in environment variables or secret managers and should never be committed to MCP configuration files.
Queries, URLs, package names, web pages, scraping outputs, dataset filters, and browser activity may be visible to Bright Data, the MCP client, and the model provider.
Public web data can still contain personal data, copyrighted content, customer information, or contractual restrictions.
Tool outputs can include scraped page text, search results, social or ecommerce dataset fields, package metadata, and browser screenshots depending on enabled tools.

Prerequisites

Node.js and npx available to the MCP client runtime.
Bright Data account and API token stored as `API_TOKEN`.
Review of Bright Data plan limits, free-tier scope, paid modes, and data-product terms.
A decision about whether to use default rapid tools, `PRO_MODE`, `GROUPS`, or explicit `TOOLS`.
Authorization to search, scrape, automate, or retrieve the target public web data.

Schema details

Install type: cli
Troubleshooting: No

Source repository stats

Scope: Source repo

Collection metadata

Estimated setup: 10 minutes
Difficulty: intermediate

Tool listing metadata

Disclosure: Uses Bright Data services, which require an account and may include free-tier, pay-as-you-go, or other plan-specific limits and charges.

Full copyable content

{
  "mcpServers": {
    "bright-data": {
      "command": "npx",
      "args": ["@brightdata/mcp"],
      "env": {
        "API_TOKEN": "YOUR_BRIGHT_DATA_API_TOKEN"
      }
    }
  }
}

About this resource

Content

Bright Data Web MCP Server connects Claude and other MCP clients to Bright Data-backed web access tools. The default server surface includes search and markdown scraping tools, while optional groups enable browser automation, ecommerce, social, finance, business, app store, travel, research, GEO, and code package-data workflows.

The package is published as @brightdata/mcp and runs as a stdio MCP server with API_TOKEN configured. The upstream server.json documents the required API token and optional environment variables for zones, pro mode, tool groups, tool allowlists, polling timeout, request timeout, retries, and rate limiting.

Source Review

These sources were reviewed on 2026-06-05. Prefer the live repository, README, package metadata, server source, tool group definitions, server manifest, license, NPM registry metadata, and Bright Data documentation for current package versions, API-token requirements, tool groups, plan details, pricing, and usage limits.

Features

Search Google, Bing, or Yandex through a Bright Data-backed search tool.
Scrape single pages as markdown and run batch scraping when enabled.
Enable browser automation tools for navigation, snapshots, screenshots, clicks, form filling, scrolling, network requests, text, and HTML extraction.
Enable ecommerce, social, finance, business, app store, travel, research, GEO, or code tool groups.
Query npm and PyPI package metadata through the code tool group.
Use GROUPS or TOOLS to restrict the exposed tool set.
Use RATE_LIMIT, timeout, and retry environment variables to bound runtime behavior.
Run as a local stdio MCP server through npx @brightdata/mcp.

Installation

Create a Bright Data API token, then configure the stdio MCP server:

{
  "mcpServers": {
    "bright-data": {
      "command": "npx",
      "args": ["@brightdata/mcp"],
      "env": {
        "API_TOKEN": "YOUR_BRIGHT_DATA_API_TOKEN"
      }
    }
  }
}

For coding-agent package lookup and research workflows, keep the exposed tool surface narrow:

{
  "mcpServers": {
    "bright-data": {
      "command": "npx",
      "args": ["@brightdata/mcp"],
      "env": {
        "API_TOKEN": "YOUR_BRIGHT_DATA_API_TOKEN",
        "GROUPS": "code,research",
        "RATE_LIMIT": "100/1h"
      }
    }
  }
}

Enable higher-impact groups only after reviewing Bright Data plan terms, request costs, and the target websites or datasets.

Use Cases

Ask Claude to retrieve current search results for a research topic.
Scrape a public webpage as markdown for summarization or extraction.
Check npm or PyPI package metadata without leaving a coding workflow.
Compare public ecommerce listings or travel data when permitted by policy and plan terms.
Run browser automation against public pages through a Bright Data-backed browser group.
Monitor public brand visibility outputs from supported LLM insight tools.

Safety and Privacy

Bright Data Web MCP Server gives an agent access to live web collection and dataset APIs. Keep scraping and browser automation within legal, contractual, and organizational policy boundaries, especially for sites with personal data, authentication gates, rate limits, or anti-abuse controls.

Use the smallest tool group that fits the task. The base search and markdown scraping tools have a different cost and risk profile than browser automation, data-product, social, or batch tools. Keep API_TOKEN and any account-specific zone configuration out of repositories, and add local rate limits before letting agents perform open-ended browsing or scraping.