Brightdata MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 10 020 installs a week from npm. Last commit 15 Sep 2026.
Bright Data's Web MCP server enabling AI agents to search, extract & navigate the web
Today is the operative word: we check Brightdata MCP every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add brightdata-mcp -- npx -y @brightdata/mcp
{
"mcpServers": {
"brightdata-mcp": {
"args": [
"-y",
"@brightdata/mcp"
],
"command": "npx"
}
}
}
[mcp_servers.brightdata-mcp]
command = "npx"
args = ["-y", "@brightdata/mcp"]
{
"mcpServers": {
"brightdata-mcp": {
"args": [
"-y",
"@brightdata/mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"brightdata-mcp": {
"args": [
"-y",
"@brightdata/mcp"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
API_TOKEN (Your API key for Bright Data), WEB_UNLOCKER_ZONE (Your unlocker zone name), BROWSER_ZONE (Your browser zone name), PRO_MODE (To enable PRO_MODE - set to true), GROUPS (Comma-separated tool group IDs (e.g., 'ecommerce,browser')), TOOLS (Comma-separated tool names to enable), POLLING_TIMEOUT (Polling timeout in seconds for web_data_* tools (default: 600)), BASE_TIMEOUT (Request timeout in seconds for base tools (search & scrape). No limit if unset), BASE_MAX_RETRIES (Max retries for base tools on transient errors (0-3, default: 0)).
The author declared them in the registry entry; get the values from the project itself.
AI-powered web research MCP server for agents. Supports web search, browse page, extract...
Open-source MCP server for AI agents: web search, content extraction, and library docs.
MCP server for LocalStack AWS services, enabling AI agents to interact with local AWS infra.
MCP server for Mudrex futures trading enabling AI agents to securely access data and risk tools.
MCP server for AI agents: discover a web page's data sources and drive the page to reach them.
Web scraping & search for AI agents: extract, SearXNG search, rerank, robots compliance. No API key.
Web access for AI agents — search/scrape/extract/crawl via the auxiliar.ai gateway.
Fetch pages as markdown, search web and news, extract structured data. For AI agents.
Answers built from our own checks of this server.