brightdata-mcp — Claude Code MCP server: search and scraping
Gives your agent live web access: search, pages as Markdown, pre-built scrapers and a remote browser. Useful when training data has no answer.
claude mcp add --env API_TOKEN=<API_TOKEN> --env WEB_UNLOCKER_ZONE=<WEB_UNLOCKER_ZONE> --env BROWSER_ZONE=<BROWSER_ZONE> --env GROUPS=<GROUPS> --env TOOLS=<TOOLS> --transport stdio brightdata-mcp -- npx -y @brightdata/mcpWhat brightdata-mcp does
The server exposes 32 tools. Search across Google, Bing and Yandex comes back as structured data, and any URL can be read as Markdown or HTML. Requests run through Bright Data's unblocking infrastructure, so bot detection, CAPTCHAs and rate limits are handled on their side — no proxy setup or headless browser to maintain.
A separate group covers the Web Scraper API: pre-built scrapers return clean JSON without HTML parsing. There is also a remote browser for navigation, clicks, typing and screenshots, plus collection of ChatGPT and Perplexity answers.
Two ways to connect: a hosted remote server behind a single URL, or a local instance via npx @brightdata/mcp. Both need an API token from your Bright Data account settings. The free tier gives 5,000 requests a month, renewing on the 1st and not rolling over; on team accounts the allowance is shared by everyone on the account. Once free requests run out, calls stop unless you have deposited funds.
What it helps with
- read a page that throws a CAPTCHA at a plain HTTP client
- pull an Amazon product listing as JSON without parsing HTML
- find current articles on a topic instead of relying on training data
- click through a site and capture a screenshot in a remote browser
- collect Google, Bing and Yandex results in one call
Example prompts for the agent
- Search the web for recent articles about this framework and read the two most relevant ones
- Scrape the competitor's pricing page as Markdown and list the plan prices
- Open the site in the browser, click the login button and screenshot the form
How to install brightdata-mcp
Platform CLI
claude mcp add --env API_TOKEN=<API_TOKEN> --env WEB_UNLOCKER_ZONE=<WEB_UNLOCKER_ZONE> --env BROWSER_ZONE=<BROWSER_ZONE> --env GROUPS=<GROUPS> --env TOOLS=<TOOLS> --transport stdio brightdata-mcp -- npx -y @brightdata/mcpReplace <…> with your own values. 2 more environment variables are in the server README
Platform CLI
codex mcp add brightdata-mcp --env API_TOKEN=<API_TOKEN> --env WEB_UNLOCKER_ZONE=<WEB_UNLOCKER_ZONE> --env BROWSER_ZONE=<BROWSER_ZONE> --env GROUPS=<GROUPS> --env TOOLS=<TOOLS> -- npx -y @brightdata/mcpReplace <…> with your own values. 2 more environment variables are in the server README
Config file
{
"mcpServers": {
"brightdata-mcp": {
"command": "npx",
"args": [
"-y",
"@brightdata/mcp"
],
"env": {
"API_TOKEN": "<API_TOKEN>",
"WEB_UNLOCKER_ZONE": "<WEB_UNLOCKER_ZONE>",
"BROWSER_ZONE": "<BROWSER_ZONE>",
"GROUPS": "<GROUPS>",
"TOOLS": "<TOOLS>"
}
}
}
}Replace <…> with your own values. 2 more environment variables are in the server README
Config file
{
"servers": {
"brightdata-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@brightdata/mcp"
],
"env": {
"API_TOKEN": "<API_TOKEN>",
"WEB_UNLOCKER_ZONE": "<WEB_UNLOCKER_ZONE>",
"BROWSER_ZONE": "<BROWSER_ZONE>",
"GROUPS": "<GROUPS>",
"TOOLS": "<TOOLS>"
}
}
}
}Replace <…> with your own values. 2 more environment variables are in the server README
Platform CLI
gemini mcp add -e API_TOKEN=<API_TOKEN> -e WEB_UNLOCKER_ZONE=<WEB_UNLOCKER_ZONE> -e BROWSER_ZONE=<BROWSER_ZONE> -e GROUPS=<GROUPS> -e TOOLS=<TOOLS> brightdata-mcp npx -y @brightdata/mcpReplace <…> with your own values. 2 more environment variables are in the server README
Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about brightdata-mcp
How do I install brightdata-mcp in Claude Code?
Run claude mcp add brightdata-mcp -e API_TOKEN=<API_TOKEN> -- npx -y @brightdata/mcp. Get the token from your Bright Data account settings.
What does brightdata-mcp do?
It hands your agent tools for web search, page reading, structured data extraction and remote browser work. Blocking and CAPTCHAs are handled by Bright Data.
What do I need to run it?
A Bright Data API token — without it the server will not connect. The free tier covers 5,000 requests a month, after which calls stop unless you have deposited funds.
