What it does

Routes scraping through Bright Data's proxy and unblocking infrastructure, which is the pragmatic answer for sites that reject datacenter IPs. The trade is cost per request and a dependency on a vendor whose pricing rewards volume. Fine for a few thousand pages, wrong for a crawl.

Install

Terminal

npx -y @brightdata/mcp

Client configuration

Paste this into your MCP client config (Claude Desktop, Cursor, or any client that reads mcpServers), then restart the client.

mcp.json

{
  "mcpServers": {
    "brightdata": {
      "command": "npx",
      "args": [
        "-y",
        "@brightdata/mcp"
      ]
    }
  }
}

Use it for

Scraping sites that block ordinary requests

Skip it if

Cheap bulk collection; you pay per request

When to use it

Reach for this when the task needs scraping inside the agent loop. Skip it if a plain shell command or a one-off script is enough — every server you add costs context and adds a failure mode.

Other TypeScript servers

Filesystem — Gives an agent scoped read, write, and search access to directories you explicitly allow
Memory — A persistent knowledge graph stored in a local JSON file, exposed through entities, relations, and observations
Sequential Thinking — Gives the model a scratchpad for structured, revisable reasoning: numbered thoughts that can branch, revise, and conclude

Bright Data MCP