Discover, extract, and interact with the web - one interface powering automated access across the public internet.
Discover, extract, and interact with the web - one interface powering automated access across the public internet.
Seamlessly connect LLMs to the live web without getting blocked
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
{
"mcpServers": {
"Bright Data": {
"command": "npx",
"args": ["@brightdata/mcp"],
"env": {
"API_TOKEN": "<your-api-token-here>"
}
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| API_TOKEN | Credential the server authenticates with. | Yes |
| GROUPS | Configuration value read at startup. | Optional |
| TOOLS | Configuration value read at startup. | Optional |
| PRO_MODE | Configuration value read at startup. | Optional |
| RATE_LIMIT | Configuration value read at startup. | Optional |
| WEB_UNLOCKER_ZONE | Configuration value read at startup. | Optional |
| BROWSER_ZONE | Configuration value read at startup. | Optional |
| POLLING_TIMEOUT | Configuration value read at startup. | Optional |
Retrieve public web pages as readable Markdown with the reference Fetch MCP server, including pagination for longer responses.
Use Firecrawl MCP to retrieve website content and extract information for research through Firecrawl’s API-backed web tools.
Read public X (Twitter) posts, threads and X Articles as clean Markdown. Read-only, no auth.
MCP server for browser automation using Puppeteer with configurable options
Investigate queries, pages, indexing and sitemaps through a read-only MCP server.
Read public web content with Evercraft; search and browser automation stay behind safety gates.