Bright Data

by Bright Data

v2.11.1

MIT

Repository Docs npm

Web & Search

scrapingproxiesweb-datasearch

Summary

Bright Data's official MCP server — search, scrape, and extract web data through a large proxy network.

Features

Search engine results and page content at scale
Structured extractors for major platforms
Proxy network that handles geo-restrictions and blocking

Installation

Set up this MCP server in your favorite AI agent — copy a ready-made configuration below.

Any MCP-compatible agent

Most agents (Claude, Cursor, Windsurf, VS Code, and more) read a standard mcpServers configuration.

Open your agent's MCP configuration file.
Merge the snippet below into it, filling in the environment variables with your own values.
Restart the agent — the "Bright Data" tools will be available.

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

Claude Code

Add the server with a single CLI command.

claude mcp add bright-data -e API_TOKEN=your-brightdata-token -- npx -y @brightdata/mcp

Claude Desktop

Add the server to claude_desktop_config.json (Settings → Developer → Edit Config).

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

Cursor

{
  "command": "npx",
  "args": [
    "-y",
    "@brightdata/mcp"
  ],
  "env": {
    "API_TOKEN": "your-brightdata-token"
  }
}

Windsurf

{
  "command": "npx",
  "args": [
    "-y",
    "@brightdata/mcp"
  ],
  "env": {
    "API_TOKEN": "your-brightdata-token"
  }
}

VS Code

{
  "command": "npx",
  "args": [
    "-y",
    "@brightdata/mcp"
  ],
  "env": {
    "API_TOKEN": "your-brightdata-token"
  }
}

Description

Bright Data's MCP server gives an assistant access to its web-data infrastructure: search results, page content, and structured extractors, all routed through a proxy network built to reach sites that block ordinary automation.

What it provides

Search across engines with real result pages rather than a cached index
Markdown scraping of any URL, with JavaScript rendering
Structured extractors for major platforms — e-commerce listings, social profiles, business directories, job posts — returning typed fields rather than raw text
Browser automation in a remote session for interactions that require it
Geo-targeting through residential proxies, so you can see what a page looks like from a specific country

Where it is the right tool

Anything at scale, and anything the target site actively defends. The trade-off is cost — this is commercial infrastructure with usage-based pricing — but it works on sites where a local scraper returns a captcha page.