# brightdata-mcp

Gives your agent live web access: search, pages as Markdown, pre-built scrapers and a remote browser. Useful when training data has no answer.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 2686
- Author: brightdata
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/brightdata/brightdata-mcp
- Updated: 2026-10-20
- HTML: https://affpapa.org/en/nevibecode/mcp/brightdata-mcp

## What it 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.

## Requirements
- Needs: Node.js (commands run via npx)
- Environment variables: `API_TOKEN`, `WEB_UNLOCKER_ZONE`, `BROWSER_ZONE`, `GROUPS`, `TOOLS`, `BASE_TIMEOUT`, `BASE_MAX_RETRIES` — keys and tokens: ask the human for the values, never commit them or put them in shared files.

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
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/mcp
```
Replace <…> with your own values. 2 more environment variables are in the server README

### Codex

**Platform CLI**
```bash
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/mcp
```
Replace <…> with your own values. 2 more environment variables are in the server README

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "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

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "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

### Gemini CLI

**Platform CLI**
```bash
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/mcp
```
Replace <…> with your own values. 2 more environment variables are in the server README

## When to use it
- 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
- 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

## Similar
- [Scrapling MCP Server](https://affpapa.org/en/nevibecode/mcp/scrapling-mcp-server.md) — MCP server · ★ 89433
- [browser-use](https://affpapa.org/en/nevibecode/mcp/browser-use.md) — MCP server · ★ 119160
- [AIHawk](https://affpapa.org/en/nevibecode/mcp/aihawk.md) — MCP server · ★ 32221
- [Skyvern](https://affpapa.org/en/nevibecode/mcp/skyvern.md) — MCP server · ★ 23263
- [SeleniumBase MCP](https://affpapa.org/en/nevibecode/mcp/seleniumbase-mcp.md) — MCP server · ★ 13169
- [apify-mcp-server](https://affpapa.org/en/nevibecode/mcp/apify-mcp-server.md) — MCP server · ★ 12927

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md