MCP Directory

How to add Bright Data MCP to Claude Desktop

All-in-one web access MCP — Web Unlocker, SERP, Scraper API, and a cloud Scraping Browser. Paste the config into ~/Library/Application Support/Claude/claude_desktop_config.json and restart Claude Desktop.

Last updated June 15, 2026 · 5.0k★ · stdio · apikey · official

Claude Desktop config for Bright Data MCP

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

Setup steps

  1. 1Open Claude Desktop → Settings → Developer → Edit Config (this opens ~/Library/Application Support/Claude/claude_desktop_config.json).
  2. 2Paste the Bright Data MCP config below under the top-level "mcpServers" key.
  3. 3Fill in any placeholder secrets (API keys, paths) in the snippet.
  4. 4Save the file, then fully quit and reopen Claude Desktop.
  5. 5Open a chat and confirm Bright Data MCP's tools appear under the 🔌 tools menu.

Before you start

  • Node.js installed (for local npx execution); not needed if you use the hosted remote server
  • A Bright Data API token — sign up at https://brightdata.com and create the token in your account (free tier available, no credit card required)
  • Set the token via the API_TOKEN environment variable (local) or the ?token= query param (hosted)

What Bright Data MCP can do in Claude Desktop

search_engine

Run an AI-optimized web search (Google/Bing/etc.) and get ranked results.

search_engine_batch

Batch multiple search-engine queries in one call.

scrape_as_markdown

Fetch a URL through Web Unlocker and return clean markdown.

scrape_batch

Scrape multiple URLs in a single batched request.

discover

AI-ranked search with intent scoring to surface the most relevant pages.

extract

AI-assisted extraction of fields from a page (Pro/advanced).

web_data_amazon_product

Structured product data from Amazon (one of 50+ web_data_* dataset tools).

web_data_linkedin_posts

Structured LinkedIn post data (social dataset).

Security

The API_TOKEN bills against your Bright Data account and PRO_MODE exposes 60+ powerful scraping tools, so keep the token in env and only enable PRO_MODE when needed. Content is fetched through Bright Data's proxy network, which sees the target URLs and returned data.

Bright Data MCP + Claude Desktop FAQ

Where is the Claude Desktop config file?

Claude Desktop reads MCP servers from ~/Library/Application Support/Claude/claude_desktop_config.json. Paste the Bright Data MCP config there under the "mcpServers" key and restart the client.

Is Bright Data MCP safe to use with Claude Desktop?

The API_TOKEN bills against your Bright Data account and PRO_MODE exposes 60+ powerful scraping tools, so keep the token in env and only enable PRO_MODE when needed. Content is fetched through Bright Data's proxy network, which sees the target URLs and returned data.

Is there a free tier?

Yes — 5,000 credits/month with no credit card required, and it auto-renews. Base tools cost 1 credit per request; web_data_* tools cost 1 credit per record returned. Unused credits don't roll over.

Do I have to install anything?

No. You can use the hosted remote server at https://mcp.brightdata.com/mcp?token=... with no install, or run it locally via npx @brightdata/mcp.

How do I enable the full set of tools?

Set PRO_MODE=true to expose all 60+ tools. For a narrower set, use the GROUPS env var (e.g. ecommerce, social, browser) or list individual tools via the TOOLS env var.

View repo Full Bright Data MCP page